© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1082
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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_9_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
    та
    1.99
     faithfully
    1.72
    под
    1.57
    $;
    1.54
    ಾ
    1.41
     forte
    1.38
    in
    1.37
     hence
    1.37
     condu
    1.34
    _;
    1.33
    POSITIVE LOGITS
    ي
    1.89
     NotImplemented
    1.89
    geführt
    1.70
    هایی
    1.68
    Ө
    1.66
    />}
    1.65
    やや
    1.63
    nf
    1.62
    संख्या
    1.62
    ;|&
    1.61
    Activations Density 0.033%

    No Known Activations