© 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. 29-GEMMASCOPE-2-RES-262K
    7. 146452
    Prev
    Next
    INDEX
    Explanations

    level up

    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
    Late
    0.76
    ereich
    0.72
     rimane
    0.68
    elas
    0.68
    endif
    0.65
     finito
    0.65
    蒨
    0.65
    iffel
    0.64
     Late
    0.64
    Sin
    0.63
    POSITIVE LOGITS
     증
    0.88
    VIAF
    0.76
    వృద్ధి
    0.74
    <unused2221>
    0.73
    활
    0.72
    氢
    0.71
    རྒྱ
    0.71
     함께
    0.70
     unions
    0.70
     tăng
    0.69
    Activations Density 0.001%

    No Known Activations