© 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. 11305
    Prev
    Next
    INDEX
    Explanations

    drawn to

    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
    ي
    3.01
    o
    2.97
    ی
    2.77
    ar
    2.74
    as
    2.70
    an
    2.66
    u
    2.66
    e
    2.62
    in
    2.57
    يّ
    2.56
    POSITIVE LOGITS
    𝘴
    2.71
    ↵↵↵
    2.60
    𝘦
    2.59
    깐
    2.57
     saturated
    2.48
    tenham
    2.44
    𝘰
    2.42
    getBy
    2.41
    𝘥
    2.40
    レクトリ
    2.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.