© 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. 200083
    Prev
    Next
    INDEX
    Explanations

    describing conditions or actions

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

    utility objects

    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
    ی
    0.53
    s
    0.51
    Ꮷ
    0.44
    ée
    0.44
    ｕ
    0.44
    两
    0.43
    one
    0.42
     થ
    0.42
    son
    0.42
     dataSource
    0.41
    POSITIVE LOGITS
     ausreiche
    0.53
     conocidos
    0.49
     উদ্দেশ্যে
    0.49
     erfüll
    0.48
     organisiert
    0.45
     gewährleisten
    0.44
    CHROM
    0.44
     kuiten
    0.43
     esclare
    0.43
    Inventory
    0.43
    Activations Density 0.001%

    No Known Activations