© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25110
    Prev
    Next
    INDEX
    Explanations

    cleaning or resetting states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ̝
    -0.92
    ()>
    -0.90
    Ⅿ
    -0.89
     celos
    -0.88
    hical
    -0.86
    )>=
    -0.82
    Inet
    -0.82
    }>;
    -0.80
    ച്ച
    -0.79
     preocupado
    -0.79
    POSITIVE LOGITS
     nor
    1.05
     tampoco
    1.02
     nothing
    0.99
    memset
    0.95
     neither
    0.93
    ߜ
    0.93
    Pherson
    0.90
     keinerlei
    0.86
     nothin
    0.85
     모든
    0.85
    Activations Density 0.004%

    No Known Activations