© 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. 127199
    Prev
    Next
    INDEX
    Explanations

    requested by user

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

    requested content and boundaries

    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
     Alcohol
    0.50
     cercanos
    0.50
     is
    0.49
     alcohol
    0.48
     ots
    0.48
     presents
    0.47
     \$
    0.46
    的時間
    0.45
    လည်း
    0.45
     Футбол
    0.44
    POSITIVE LOGITS
    Technische
    0.57
    ze
    0.55
    ха
    0.53
    ę
    0.48
    hai
    0.47
    ceu
    0.46
    {|\
    0.46
    adığı
    0.45
    "%(
    0.45
    珵
    0.44
    Activations Density 0.001%

    No Known Activations