© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211962
    Prev
    Next
    INDEX
    Explanations

    questions, exclamations, or phrases ending in punctuation

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

    completions or substitutions

    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
    Negative Logits
     মুসল
    0.45
    arently
    0.45
     সর্বো
    0.43
    сне
    0.43
     અલગ
    0.42
     했
    0.42
     વિવિધ
    0.42
     ಇರುವ
    0.42
     ござい
    0.41
     ያለው
    0.41
    POSITIVE LOGITS
     Elisabeth
    0.47
     Å
    0.43
    produktion
    0.42
     /
    0.42
     Fame
    0.42
     Cram
    0.41
     Fred
    0.40
     appliqu
    0.40
     Hubert
    0.40
     They
    0.39
    Activations Density 0.002%

    No Known Activations