© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2746
    Prev
    Next
    INDEX
    Explanations

    recorded in context

    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_22_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
    <unused2126>
    0.70
    <unused2165>
    0.68
     simb
    0.65
    ススメ
    0.64
     참
    0.64
    <unused1084>
    0.64
     전문가
    0.61
     foment
    0.61
     serendip
    0.61
     tatu
    0.60
    POSITIVE LOGITS
    Being
    0.74
    Backed
    0.73
    氯
    0.72
     जीबी
    0.72
    Fac
    0.72
    šč
    0.72
    ELLE
    0.71
    Ss
    0.71
     BEING
    0.70
     পুর্ব
    0.70
    Activations Density 3.073%

    No Known Activations