© 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. 29-GEMMASCOPE-2-RES-262K
    7. 148819
    Prev
    Next
    INDEX
    Explanations

    string manipulation code

    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_29_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
    ।.
    0.75
    -.
    0.73
     жиз
    0.66
    (.
    0.64
     күз
    0.64
    ^{-}
    0.64
    <0xA6>
    0.64
     idempotent
    0.63
    ꯟ
    0.63
     पहचा
    0.62
    POSITIVE LOGITS
     opiek
    0.78
    赟
    0.76
     Metallica
    0.74
     hCG
    0.72
     كتابه
    0.71
    ")){
    0.71
    augh
    0.70
    诹
    0.70
     Büh
    0.70
    msubsup
    0.70
    Activations Density 0.002%

    No Known Activations