© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102825
    Prev
    Next
    INDEX
    Explanations

    xhtml doctype

    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_34/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
     Hinata
    -0.78
    quelles
    -0.77
     WISCONSIN
    -0.75
    ⠄
    -0.72
    digits
    -0.71
    гъл
    -0.71
     wies
    -0.70
     verrou
    -0.70
     SENATE
    -0.69
    Rispondi
    -0.68
    POSITIVE LOGITS
    леб
    0.71
    record
    0.69
     Dri
    0.65
     Schal
    0.64
    likopter
    0.62
    FIS
    0.62
     Tuna
    0.60
    尺
    0.59
    }$}
    0.59
     участ
    0.59
    Activations Density 0.052%

    No Known Activations