© 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. 39459
    Prev
    Next
    INDEX
    Explanations

    at your option/discretion

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

    summit success, collects DNA

    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
    דע
    0.45
    ルート
    0.43
    utilisateur
    0.43
    ﮢ
    0.43
    routine
    0.43
    欲
    0.42
    רט
    0.41
    ौरा
    0.41
     অভিনেত্রী
    0.41
    ρι
    0.40
    POSITIVE LOGITS
     pleads
    0.61
     plead
    0.54
     Á
    0.52
    okovic
    0.52
     Krist
    0.51
     Kü
    0.50
     elig
    0.49
     Ferrer
    0.49
     krist
    0.49
     guter
    0.49
    Activations Density 0.000%

    No Known Activations