© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10823
    Prev
    Next
    INDEX
    Explanations

    body parts and chassis

    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
    ية
    1.11
    ковка
    0.93
     việc
    0.87
    adolid
    0.86
    vedi
    0.84
    ribution
    0.83
    pendiente
    0.82
     $,
    0.82
    铛
    0.82
    fdata
    0.81
    POSITIVE LOGITS
    𝘵
    0.80
    에
    0.76
    deleted
    0.71
    unix
    0.69
     unterwegs
    0.68
    de
    0.66
     kwargs
    0.66
    𝘳
    0.66
    esine
    0.65
     বঙ্গের
    0.64
    Activations Density 0.116%

    No Known Activations