© 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. 22-GEMMASCOPE-2-RES-262K
    7. 3524
    Prev
    Next
    INDEX
    Explanations

    time durations in hours or minutes

    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_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
    告訴
    0.56
    Enable
    0.56
    estas
    0.55
    Eval
    0.55
    Ổ
    0.54
    eval
    0.54
    As
    0.54
    长
    0.53
    ZIE
    0.53
    晴
    0.53
    POSITIVE LOGITS
     tinkering
    0.62
     poking
    0.62
     antics
    0.61
     wording
    0.57
     hangout
    0.57
     treads
    0.57
     busier
    0.56
     vibes
    0.56
     curation
    0.56
     shenanigans
    0.56
    Activations Density 0.017%

    No Known Activations