© 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. 173912
    Prev
    Next
    INDEX
    Explanations

    ability to

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

    riddle logic

    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
    nite
    0.48
     請
    0.47
     characterized
    0.46
     characterizing
    0.45
    詡
    0.45
    阿拉伯
    0.44
    eni
    0.44
     fried
    0.44
     pronouncing
    0.44
    慄
    0.43
    POSITIVE LOGITS
     влади
    0.49
    Кар
    0.46
    Cursor
    0.46
    жет
    0.45
    тся
    0.45
    Shares
    0.44
    образова
    0.44
     dogged
    0.42
    Cargo
    0.42
    പോ
    0.41
    Activations Density 0.002%

    No Known Activations