© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4101
    Prev
    Next
    INDEX
    Explanations

    refine and improve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𝗮
    3.07
    蒻
    2.98
    𝗸
    2.92
    𝘂
    2.86
    𝗻
    2.84
    謹
    2.82
    lük
    2.79
    kiej
    2.78
    spr
    2.72
    𝗼
    2.70
    POSITIVE LOGITS
    ि
    3.19
    TE
    2.95
    ות
    2.92
    ی
    2.88
    는
    2.58
    setCharacter
    2.57
    ed
    2.56
    ┛
    2.37
    ண்ணாம
    2.36
    o
    2.31
    Activations Density 0.034%

    No Known Activations