© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12166
    Prev
    Next
    INDEX
    Explanations

    query parameters and params

    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_9_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
    ي
    2.43
    ה
    2.22
    מה
    2.00
    ruce
    1.97
     także
    1.97
     extremity
    1.96
     CGRect
    1.91
    к
    1.89
    ు
    1.88
    тэй
    1.83
    POSITIVE LOGITS
    ai
    2.31
    ా
    2.31
     étoile
    2.24
    ে
    2.23
     lomba
    2.19
    エリ
    2.19
    هره
    2.18
    o
    2.12
    ｶ
    2.11
    ϻ
    2.10
    Activations Density 0.000%

    No Known Activations