© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1826
    Prev
    Next
    INDEX
    Explanations

    markers and code formatting

    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
    يتي
    2.67
    ᵖ
    2.66
    hnung
    2.63
    itie
    2.62
    ┬
    2.61
    为一个
    2.56
    asion
    2.55
    ignant
    2.52
    ibfk
    2.51
    谓
    2.45
    POSITIVE LOGITS
    ra
    2.87
    もら
    2.70
    s
    2.65
    geom
    2.64
    osť
    2.61
    ruz
    2.47
    うま
    2.42
     
    2.38
    నే
    2.36
    nelle
    2.36
    Activations Density 0.144%

    No Known Activations