© 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. 123657
    Prev
    Next
    INDEX
    Explanations

    Bill of lading

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

    punctuation and common words

    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
     zich
    0.46
    }$,
    0.45
    kitchen
    0.44
    воз
    0.44
     son
    0.43
     sparse
    0.43
    rugu
    0.41
     ы
    0.41
    get
    0.41
     voiced
    0.41
    POSITIVE LOGITS
     ಸ್ಥ
    0.52
    चर्स
    0.50
    唂
    0.48
     দুর
    0.48
    িয়ন
    0.48
     অবন
    0.46
    PAIR
    0.46
    namento
    0.46
    থ্যা
    0.46
    絆
    0.46
    Activations Density 0.000%

    No Known Activations