© 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. 4016
    Prev
    Next
    INDEX
    Explanations

    translate language

    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
    tica
    3.31
    t
    3.28
    tic
    3.25
    tz
    3.10
    tj
    2.86
    tl
    2.85
    tm
    2.83
    tics
    2.74
    tion
    2.64
    tions
    2.61
    POSITIVE LOGITS
    ة
    3.01
    romptu
    2.68
    ES
    2.55
    ھی
    2.50
     gal
    2.43
     NULL
    2.40
    hetamine
    2.39
    createServer
    2.38
    сім
    2.35
    льский
    2.32
    Activations Density 0.016%

    No Known Activations