© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231297
    Prev
    Next
    INDEX
    Explanations

    child or minors

    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
     Эк
    0.50
     اک
    0.50
     Архі
    0.47
     буди
    0.46
     Burundi
    0.46
     까
    0.46
     Genres
    0.45
     ecclesiastical
    0.45
    дування
    0.45
     ακ
    0.44
    POSITIVE LOGITS
    r
    0.52
    a
    0.52
    न
    0.50
    an
    0.49
    in
    0.47
     neki
    0.46
    LastName
    0.44
    лив
    0.44
    isible
    0.44
    िक
    0.43
    Activations Density 0.001%

    No Known Activations