© 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. 254635
    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
    ฮ
    0.52
    ור
    0.51
    ликт
    0.49
    ificare
    0.48
    роятно
    0.48
    ihad
    0.47
    Москва
    0.47
    руса
    0.47
    jeron
    0.47
    kannya
    0.47
    POSITIVE LOGITS
     صدای
    0.49
     غ
    0.48
     polyd
    0.46
     polyvinyl
    0.45
    ئ
    0.44
     اجرای
    0.44
     کنس
    0.44
     ئ
    0.44
     اک
    0.44
     unconscious
    0.44
    Activations Density 0.001%

    No Known Activations