© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32112
    Prev
    Next
    INDEX
    Explanations

    resisting arrest

    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
     Infla
    -0.75
    惩罚
    -0.75
     背景
    -0.74
    пьютер
    -0.73
     aceto
    -0.72
    EXTER
    -0.71
    Laughter
    -0.69
     Veggie
    -0.68
     Illumin
    -0.68
    iterate
    -0.68
    POSITIVE LOGITS
     resistance
    2.31
     resisting
    2.27
     resist
    2.20
     Resistance
    2.02
     resisted
    1.99
    resistance
    1.95
    Resist
    1.84
    resist
    1.83
     Resist
    1.81
    Resistance
    1.80
    Activations Density 0.011%

    No Known Activations