© 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. 178677
    Prev
    Next
    INDEX
    Explanations

    months and specific nouns

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

    vector embeddings, alpaca, potential

    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
    وغ
    0.49
    他对
    0.45
    㯎
    0.45
    وذ
    0.44
    ﻦ
    0.44
    이라고
    0.44
    货
    0.44
     ফান্ড
    0.44
    他又
    0.44
    υ
    0.44
    POSITIVE LOGITS
     November
    0.51
    ,—
    0.49
     July
    0.46
     February
    0.46
    curses
    0.46
    -/-
    0.46
     goddess
    0.46
     **)
    0.45
     NOVEMBER
    0.45
     flounder
    0.44
    Activations Density 0.001%

    No Known Activations