© 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. 39356
    Prev
    Next
    INDEX
    Explanations

    SE followed by common abbreviations or place names

    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
    .
    -3.92
    “
    -3.19
     
    -2.83
    ↵↵
    -2.80
    /
    -2.75
      
    -2.72
    —
    -2.69
    </em>
    -2.50
    ли
    -2.47
    也
    -2.47
    POSITIVE LOGITS
    鯡
    2.92
    ᡨ
    2.70
     bezpeč
    2.70
    岖
    2.63
    poptotic
    2.63
    
    2.63
    Ꮉ
    2.58
    ophageal
    2.58
    茼
    2.56
     新款
    2.55
    Activations Density 0.012%

    No Known Activations