© 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. 10-GEMMASCOPE-RES-131K
    7. 99092
    Prev
    Next
    INDEX
    Explanations

    stressful situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </td>
    -2.81
    噲
    -2.78
     лучший
    -2.72
    ৄ
    -2.39
    gigabyte
    -2.34
    ?
    -2.33
    änemark
    -2.31
    蝙
    -2.20
    饧
    -2.09
     a
    -2.08
    POSITIVE LOGITS
    time
    2.63
    that
    2.45
     нам
    2.44
    by
    2.44
    to
    2.39
    our
    2.31
     frantic
    2.23
    镡
    2.20
    ties
    2.14
    Even
    2.13
    Activations Density 0.003%

    No Known Activations