© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16314
    Prev
    Next
    INDEX
    Explanations

    electoral redistribution

    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
    Not in Any Lists

    No Comments

    Negative Logits
     وصلة
    -1.35
     αὐ
    -1.35
    ')->
    -1.34
    ministrazione
    -1.30
     αὐτ
    -1.28
    ุทธ
    -1.26
    思議
    -1.25
    nachweise
    -1.25
     лимон
    -1.24
    思议
    -1.24
    POSITIVE LOGITS
    ִּ
    1.42
     will
    1.34
    complished
    1.25
    mici
    1.23
     analysis
    1.18
    によって
    1.14
     anew
    1.13
    ֵּ
    1.13
    ַּ
    1.12
     hicimos
    1.11
    Activations Density 0.042%

    No Known Activations