© 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. 4173
    Prev
    Next
    INDEX
    Explanations

    statistical mean

    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
    s
    2.47
    t
    2.34
    c
    2.34
    erious
    2.25
    т
    2.18
    alek
    2.04
    iotic
    2.01
    ת
    1.96
    tls
    1.93
    ravenous
    1.93
    POSITIVE LOGITS
    辕
    2.22
    CommonAncestor
    2.19
    veis
    2.11
    দুই
    2.03
    onRouteChange
    2.00
    ണി
    1.96
     bildet
    1.96
     zählt
    1.94
    ℚ
    1.92
    轅
    1.89
    Activations Density 0.100%

    No Known Activations