© 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. 255198
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    __:
    0.49
     câncer
    0.47
    sq
    0.46
     côtes
    0.46
     eateries
    0.45
     celles
    0.45
    repositories
    0.45
    깝
    0.45
     دیگری
    0.45
     Garvey
    0.45
    POSITIVE LOGITS
     अपनाने
    0.49
    нде
    0.45
     ввод
    0.44
     consta
    0.44
    ыр
    0.42
     അംഗ
    0.42
    ところが
    0.42
    ნა
    0.42
     பிறகு
    0.41
    ところに
    0.41
    Activations Density 0.001%

    No Known Activations