© 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. 56105
    Prev
    Next
    INDEX
    Explanations

    break out or play out

    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
    وبر
    -0.77
    attre
    -0.75
    ம்
    -0.73
     domesticated
    -0.72
    дизайн
    -0.71
     podla
    -0.71
     spille
    -0.69
     artikkelen
    -0.69
    红了
    -0.68
    детская
    -0.67
    POSITIVE LOGITS
    out
    1.24
    outs
    0.90
    アウト
    0.89
    OUT
    0.82
    dout
    0.78
    Defs
    0.75
    στο
    0.74
    房间
    0.73
     вме
    0.73
    Out
    0.73
    Activations Density 0.058%

    No Known Activations