© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6562
    Prev
    Next
    INDEX
    Explanations

    potential risks and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Authentication
    1.94
    íj
    1.93
    рата
    1.92
     gleichen
    1.88
    ieval
    1.87
    ╕
    1.86
     Kerm
    1.86
     QPushButton
    1.86
     antich
    1.85
     同
    1.85
    POSITIVE LOGITS
    finale
    0.95
    バランス
    0.74
    oples
    0.70
    including
    0.69
    インパクト
    0.68
    truncated
    0.68
    Mills
    0.67
    Mind
    0.67
    impact
    0.67
    ultura
    0.65
    Activations Density 0.016%

    No Known Activations