© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13346
    Prev
    Next
    INDEX
    Explanations

    World Wars, tutorial, cats, building

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jobSearch
    1.53
    FAO
    1.44
     strokeWeight
    1.43
     rectMode
    1.42
     gridSize
    1.41
     concat
    1.41
    Ⴖ
    1.39
     globalMap
    1.39
    cosystem
    1.39
     onRouteChange
    1.37
    POSITIVE LOGITS
    s
    1.24
    si
    1.18
    yat
    1.17
    san
    1.10
    ial
    1.07
    n
    1.06
    sign
    1.06
    ာ
    1.05
    ات
    1.04
    rines
    1.04
    Activations Density 0.000%

    No Known Activations