© 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. 107452
    Prev
    Next
    INDEX
    Explanations

    Unlike other

    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
    siu
    -0.85
     CMO
    -0.78
     geben
    -0.72
    addRow
    -0.69
    SEE
    -0.65
    檢查
    -0.64
    borderBottom
    -0.64
    Confira
    -0.64
    seless
    -0.63
     harassing
    -0.63
    POSITIVE LOGITS
     Szer
    0.79
    coherent
    0.73
     sentir
    0.69
     DEAL
    0.69
     trato
    0.69
    を書く
    0.68
    ád
    0.68
     Vay
    0.66
     inglés
    0.66
     Kho
    0.66
    Activations Density 0.073%

    No Known Activations