© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    Oh no I; after third, wrongful, female

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     Beled
    1.77
    合格
    1.69
    ЦИ
    1.68
    线
    1.68
    Pull
    1.65
    زء
    1.64
     Combustion
    1.62
     Countdown
    1.61
     Especial
    1.61
     dado
    1.60
    POSITIVE LOGITS
    }^{+
    2.05
     cyclical
    1.91
     isomer
    1.88
    tobago
    1.88
    chae
    1.86
    ္ဂ
    1.86
    mapping
    1.85
    iju
    1.84
    shoring
    1.84
    chh
    1.82
    Activations Density 0.000%

    No Known Activations