© 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. 128158
    Prev
    Next
    INDEX
    Explanations

    social aspects and outcomes

    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
     It
    -2.05
     but
    -1.74
     utilizing
    -1.52
     our
    -1.52
     However
    -1.40
    ers
    -1.38
    asticity
    -1.38
     Як
    -1.37
     Some
    -1.35
    瞩
    -1.35
    POSITIVE LOGITS
    ↵
    1.76
    茈
    1.65
     سيارة
    1.38
    已经
    1.37
    </em>
    1.37
     desses
    1.37
    4
    1.35
    yorlar
    1.35
    場合は
    1.32
    antes
    1.30
    Activations Density 0.014%

    No Known Activations