© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162095
    Prev
    Next
    INDEX
    Explanations

    locations or categories

    np_acts-logits-general · gemini-2.5-flash-lite

    greetings, foreign languages, specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    潇
    0.46
    entlich
    0.45
    5
    0.43
     вновь
    0.42
    Comments
    0.42
    ენტ
    0.42
     Hobby
    0.41
    Media
    0.41
    Shah
    0.39
    FI
    0.39
    POSITIVE LOGITS
    
    0.49
     ALEX
    0.49
     gods
    0.48
     operat
    0.46
     aç
    0.45
     Å
    0.45
     Celest
    0.45
     negócio
    0.44
     repayment
    0.43
     JEAN
    0.43
    Activations Density 0.001%

    No Known Activations