© 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. 199327
    Prev
    Next
    INDEX
    Explanations

    contact with. our team. writers

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

    gratitude, engineering, dog walker

    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
     Ballarat
    0.49
    的
    0.48
     sanitaria
    0.48
    صرية
    0.48
    靜
    0.48
     کړئ
    0.46
    сл
    0.46
    來到
    0.45
    ס
    0.45
     Saviour
    0.44
    POSITIVE LOGITS
    ians
    0.50
    ions
    0.49
    okban
    0.49
    itya
    0.47
    ants
    0.47
    igs
    0.47
    rahm
    0.47
    ikh
    0.46
    rape
    0.46
    akty
    0.45
    Activations Density 0.005%

    No Known Activations