© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34251
    Prev
    Next
    INDEX
    Explanations

    technical or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on the leading prefixes of long, multi-syllable technical or “big” words (e.g. sel- from self-, mor- from mortgage, con- from constraining, cri- from cricotracheal, Sep- from septal, re- from reCaptcha, sup-/ern-/at- from supernatural, pro- from proscribed, ind- from indgår, conf- from conflation, etc.). In other words, it detects the start of lengthy, often Latin-derived content words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     великолеп
    -1.70
    itename
    -1.38
    referred
    -1.38
    considered
    -1.34
     longterm
    -1.33
    ihnachts
    -1.33
     amorti
    -1.32
    representing
    -1.30
     DIFFERENT
    -1.24
    launched
    -1.24
    POSITIVE LOGITS
     even
    1.26
    .
    1.11
     not
    1.08
     on
    1.08
    )
    1.07
    !
    1.06
     immensely
    1.03
    ಈ
    1.02
     or
    1.02
     now
    1.02
    Activations Density 0.186%

    No Known Activations