© 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. 146613
    Prev
    Next
    INDEX
    Explanations

    then, after

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

    explaining new terms, concepts, and patterns

    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
    லில்
    0.45
     философии
    0.44
    Poems
    0.44
     চাহিল
    0.43
     অর্চনা
    0.43
    铍
    0.43
    Alchemy
    0.43
    Lista
    0.43
    భా
    0.43
    িক্ষে
    0.42
    POSITIVE LOGITS
     happening
    0.46
     unhappy
    0.46
    斬
    0.45
     overtaking
    0.44
     causing
    0.44
     đang
    0.44
     during
    0.43
     crossing
    0.43
    」
    0.43
     customary
    0.43
    Activations Density 0.000%

    No Known Activations