© 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. 205838
    Prev
    Next
    INDEX
    Explanations

    run away

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

    symbols and punctuation

    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
    硯
    0.51
    izi
    0.49
     digitales
    0.49
     Digital
    0.47
    ргани
    0.47
     sintering
    0.46
     digitized
    0.46
     defying
    0.46
    serr
    0.46
     on
    0.45
    POSITIVE LOGITS
     Portsmouth
    0.54
    VII
    0.50
     keySchedule
    0.49
    `;
    0.45
    ChooseCharacter
    0.44
    Durham
    0.44
    kernel
    0.44
    ::*;
    0.43
     三角
    0.43
     Marlene
    0.43
    Activations Density 0.000%

    No Known Activations