© 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. 129573
    Prev
    Next
    INDEX
    Explanations

    "it" followed by simple, assisted, or next year

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

    incredibly satisfying or frustrating

    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
    ur
    0.59
    al
    0.57
    i
    0.56
    er
    0.55
    jets
    0.54
    iin
    0.54
    prima
    0.54
    MG
    0.52
    xious
    0.52
    h
    0.50
    POSITIVE LOGITS
     सहायता
    0.53
    芪
    0.49
     škol
    0.46
     वैकेंसी
    0.45
     modalidad
    0.43
     liggen
    0.43
    谎
    0.43
    সপ
    0.43
     luchar
    0.43
     adiab
    0.43
    Activations Density 0.001%

    No Known Activations