© 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-16K
    7. 2593
    Prev
    Next
    INDEX
    Explanations

    affidavit, beard, brackets, compost, compositing, household, jaw, mood, tomorrow

    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_16k_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
    UInt
    2.84
    р
    2.79
    Bingo
    2.72
     malloc
    2.58
    uksen
    2.58
    тической
    2.58
    ти
    2.57
    vivo
    2.54
    moire
    2.46
    ergy
    2.44
    POSITIVE LOGITS
    要
    3.43
    ant
    3.31
    ра
    3.13
    ী
    3.06
    ح
    2.99
     pickle
    2.94
     Meinung
    2.82
    शियों
    2.81
     shutdowns
    2.80
    那就是
    2.79
    Activations Density 0.242%

    No Known Activations