© 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. 167744
    Prev
    Next
    INDEX
    Explanations

    keywords followed by related nouns

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

    ERP, PDF, continuous learning

    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
     Gött
    0.50
     Serum
    0.49
     nonradiative
    0.49
     Elsie
    0.48
     Elektr
    0.46
    𖥔
    0.46
     Beton
    0.46
     chromospheres
    0.46
     Theodor
    0.45
     Rossi
    0.45
    POSITIVE LOGITS
     exploded
    0.54
     ripped
    0.50
    heard
    0.50
     mocked
    0.48
     off
    0.47
    ﻪ
    0.46
     generated
    0.46
    ンの
    0.46
     edged
    0.46
     cập
    0.46
    Activations Density 0.000%

    No Known Activations