© 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. 34-GEMMASCOPE-RES-131K
    7. 30477
    Prev
    Next
    INDEX
    Explanations

    criminal acts

    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
     арт
    -0.84
     individuales
    -0.74
     like
    -0.72
     Bandar
    -0.71
    والي
    -0.71
     Ostra
    -0.70
    虢
    -0.69
    स्
    -0.67
    次回
    -0.66
     gmail
    -0.65
    POSITIVE LOGITS
    echa
    0.82
     الدولة
    0.81
     ด้วย
    0.80
     tollen
    0.79
    sitive
    0.79
    Gill
    0.77
     giết
    0.75
     参数
    0.75
     tumultuous
    0.75
    TET
    0.73
    Activations Density 0.026%

    No Known Activations