© 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. 145843
    Prev
    Next
    INDEX
    Explanations

    SparkSession builder

    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
    മുള്ള
    0.70
     издание
    0.68
     ketiga
    0.64
     svenska
    0.64
    ด้
    0.62
    Confusion
    0.61
    ით
    0.61
    서
    0.61
     mimetype
    0.60
     sputum
    0.60
    POSITIVE LOGITS
     pengh
    0.75
     tans
    0.73
     Reverse
    0.71
    RAS
    0.66
     crowds
    0.63
    requency
    0.63
    reverse
    0.62
     reverse
    0.62
     beat
    0.62
    adt
    0.62
    Activations Density 0.004%

    No Known Activations