© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25394
    Prev
    Next
    INDEX
    Explanations

    citing dates and numbers

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

    This neuron fires strongly on rare or irregular tokens—like partial morphemes, hyphenated compounds, or other low‐frequency string fragments.

    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
     on
    -1.55
     if
    -1.27
     while
    -1.20
     where
    -1.20
     when
    -1.14
     by
    -1.13
     at
    -1.12
    …..
    -1.09
     If
    -1.09
     that
    -1.09
    POSITIVE LOGITS
     who
    1.49
    𓆏
    1.45
    ⚢
    1.42
     bụ
    1.34
    primarily
    1.32
    mostly
    1.32
     everyone
    1.29
    𓆸
    1.28
    𓁹
    1.27
     cóc
    1.27
    Activations Density 0.044%

    No Known Activations