© 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. 72529
    Prev
    Next
    INDEX
    Explanations

    levels of increasing difficulty

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

    The neuron preferentially fires on longer, lower‐frequency content words—especially multi­syllabic or technical terms.

    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
     their
    -1.54
     like
    -1.53
     all
    -1.44
     support
    -1.28
    тистика
    -1.23
     mereka
    -1.20
    fficacy
    -1.19
    自己的
    -1.16
     помогает
    -1.13
    InputBorder
    -1.13
    POSITIVE LOGITS
    ৷
    1.28
    门的
    1.20
     begyn
    1.19
    妩
    1.19
    嚕
    1.18
     概要
    1.15
    !==
    1.13
    ῦ
    1.13
    widetilde
    1.13
    各样的
    1.13
    Activations Density 0.097%

    No Known Activations