© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9008
    Prev
    Next
    INDEX
    Explanations

    classifications and roles

    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
    л
    0.94
    して
    0.75
    ार्थियों
    0.72
    াদার
    0.71
    <unused1082>
    0.69
     την
    0.68
     Immunohist
    0.67
    ParaName
    0.64
     Versand
    0.64
    ل
    0.64
    POSITIVE LOGITS
    ET
    0.90
    ட
    0.64
    перь
    0.64
    IF
    0.63
    Hill
    0.62
    ETIC
    0.61
     Trag
    0.61
    EL
    0.61
    OGEN
    0.60
    గి
    0.60
    Activations Density 0.005%

    No Known Activations