© 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. 15039
    Prev
    Next
    INDEX
    Explanations

    javascript code using jQuery

    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
     Actually
    -2.77
     If
    -2.48
     Since
    -2.47
     a
    -2.44
     Much
    -2.41
     Not
    -2.41
    to
    -2.33
    𖥧
    -2.31
     Even
    -2.23
     Anyway
    -2.22
    POSITIVE LOGITS
    }$
    2.64
    ⸫
    2.48
    ſſen
    2.45
    峮
    2.42
    ఽ
    2.33
    ଯ
    2.30
     создания
    2.27
    ￳
    2.27
     性感
    2.25
    
    2.25
    Activations Density 0.010%

    No Known Activations