© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6807
    Prev
    Next
    INDEX
    Explanations

    role of

    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_22_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
     сти
    1.01
    ಕಾರ
    1.01
    젠
    0.98
    зиру
    0.93
    лость
    0.89
    맴
    0.89
    kezi
    0.89
    谯
    0.88
    소스
    0.87
    ))->
    0.87
    POSITIVE LOGITS
    forward
    1.37
    carried
    1.31
     Carrying
    1.31
     forward
    1.25
     Carry
    1.23
    Forward
    1.22
    Carry
    1.20
    carrying
    1.19
     carried
    1.18
    Weight
    1.16
    Activations Density 0.035%

    No Known Activations