© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7731
    Prev
    Next
    INDEX
    Explanations

    Vue Router components

    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_12_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
    ضيف
    2.25
    rega
    2.14
    cous
    2.10
    내는
    2.09
    NIA
    2.08
    꾼
    2.04
     خارجية
    2.00
    asketball
    1.95
    >|</
    1.93
    unks
    1.92
    POSITIVE LOGITS
     Calend
    2.22
     Almost
    2.20
    Paths
    1.95
     Virtually
    1.93
     Nearly
    1.89
     Hob
    1.88
     Governance
    1.85
    Almost
    1.84
     Blossom
    1.84
    Calend
    1.82
    Activations Density 0.000%

    No Known Activations