© 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-262K
    7. 9681
    Prev
    Next
    INDEX
    Explanations

    scalar field or unsigned int

    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_262k_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
    jeni
    1.21
    quia
    1.06
    콤
    1.00
    getto
    0.99
    র্প
    0.98
    ная
    0.98
    quelle
    0.97
    htub
    0.97
    SPECT
    0.96
    гия
    0.95
    POSITIVE LOGITS
    دن
    1.58
    म
    1.54
    ੀ
    1.45
    ش
    1.41
    氲
    1.40
    ت
    1.39
    );//
    1.38
     alken
    1.36
    RMSE
    1.35
    */}
    1.35
    Activations Density 0.000%

    No Known Activations