© 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. 117457
    Prev
    Next
    INDEX
    Explanations

    procedures under or such as

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

    dog who's, require, lawn ornaments

    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
     siglo
    0.49
    ing
    0.48
     func
    0.45
     utils
    0.45
    ↵
    0.44
     lang
    0.43
     slog
    0.43
     listen
    0.42
     league
    0.42
     Naciones
    0.42
    POSITIVE LOGITS
     刺繍
    0.55
    களை
    0.52
     ойнотуу
    0.52
     хто
    0.51
     공연
    0.49
    کش
    0.48
    тності
    0.48
    荖
    0.47
    Tocco
    0.47
    뎐
    0.47
    Activations Density 0.000%

    No Known Activations