© 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. 10327
    Prev
    Next
    INDEX
    Explanations

    terms of service and conditions

    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
    ه
    2.37
    o
    2.37
    ted
    2.31
    e
    2.26
    te
    2.09
    ে
    2.06
    uZ
    1.98
    на
    1.96
    to
    1.93
    ty
    1.92
    POSITIVE LOGITS
    Н
    1.92
     प्रावधान
    1.80
    दार
    1.73
     nuances
    1.69
    র্
    1.67
    вки
    1.66
     stripes
    1.65
    饵
    1.63
     conformidad
    1.62
     deine
    1.60
    Activations Density 0.062%

    No Known Activations