© 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. 44258
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
    雠
    -3.30
    脔
    -3.11
    鼍
    -2.89
    읊
    -2.80
     parachoque
    -2.80
    ୌ
    -2.56
    粜
    -2.56
    櫺
    -2.55
    鸶
    -2.55
     teater
    -2.55
    POSITIVE LOGITS
     
    3.05
     If
    2.80
     While
    2.75
     According
    2.64
     in
    2.63
     Also
    2.58
     often
    2.52
     as
    2.50
     at
    2.48
     It
    2.45
    Activations Density 0.123%

    No Known Activations