© 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. 7597
    Prev
    Next
    INDEX
    Explanations

    code and data parsing

    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
    ú
    2.01
    north
    1.87
    Reality
    1.86
    ±
    1.85
     NUS
    1.85
    Slice
    1.85
    nur
    1.81
    UST
    1.79
    flipped
    1.77
    SW
    1.77
    POSITIVE LOGITS
     engines
    0.88
    ések
    0.84
    erosene
    0.82
     Engines
    0.81
     }}$.
    0.80
     groupBy
    0.79
    endus
    0.78
     меда
    0.77
     errorHandler
    0.77
    $.}
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.