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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66339
    Prev
    Next
    INDEX
    Explanations

    Prakash Raj, Balaprakash, Park City, Akalis

    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_34/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
     مز
    -0.72
     Vy
    -0.70
    武士
    -0.70
     parallels
    -0.70
    ALLEL
    -0.69
    nyez
    -0.68
     finitely
    -0.67
     epit
    -0.67
    mover
    -0.67
    Bingo
    -0.66
    POSITIVE LOGITS
     jendela
    0.76
    rant
    0.75
    anyol
    0.73
    思想
    0.69
    }}^
    0.68
     ótima
    0.68
     pikiran
    0.67
    やる
    0.67
     Gillespie
    0.66
     quale
    0.66
    Activations Density 0.037%

    No Known Activations