© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34986
    Prev
    Next
    INDEX
    Explanations

    terms being defined

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

    The neuron fires on subword pieces of specialized jargon or compound technical terms (including proper names) in the text.

    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
     Vám
    -1.47
     recém
    -1.39
    lxt
    -1.34
     automó
    -1.30
     extremamente
    -1.30
     generó
    -1.28
     AMAZING
    -1.25
     hinzugefügt
    -1.25
     amazingly
    -1.25
     broader
    -1.25
    POSITIVE LOGITS
     not
    1.77
     because
    1.76
     or
    1.58
     first
    1.43
     so
    1.34
     as
    1.32
     k
    1.32
     no
    1.29
     before
    1.27
     one
    1.25
    Activations Density 0.096%

    No Known Activations