© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 679
    Prev
    Next
    INDEX
    Explanations

    enumerated lists

    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
    '
    2.07
    .
    1.82
    -
    1.80
    с
    1.78
     because
    1.70
    of
    1.70
    (
    1.70
    Although
    1.67
     and
    1.65
    ంద్
    1.62
    POSITIVE LOGITS
     dessen
    2.04
     deren
    2.00
    ैमर
    1.83
    밂
    1.82
    ванович
    1.79
    setGeometry
    1.76
    uiDesigner
    1.74
     entferne
    1.74
    Ӏо
    1.70
    िक्की
    1.68
    Activations Density 1.113%

    No Known Activations