© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1868
    Prev
    Next
    INDEX
    Explanations

    parenthesized links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inschaft
    0.71
    吿
    0.64
    entieth
    0.63
    ỡ
    0.63
     되겠죠
    0.63
    యితే
    0.63
    ăr
    0.62
    %");
    0.62
    amides
    0.59
    cellaneous
    0.59
    POSITIVE LOGITS
     https
    4.99
    https
    4.61
     http
    4.47
    http
    4.12
     www
    3.99
    www
    3.42
    ttps
    2.75
    Https
    2.25
     Http
    2.19
     [
    2.12
    Activations Density 0.594%

    No Known Activations