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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 170475
    Prev
    Next
    INDEX
    Explanations

    but I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    타
    0.52
    ISTS
    0.46
    林
    0.45
    ະລ
    0.45
    اک
    0.44
    kimi
    0.44
    Millis
    0.44
    火车
    0.43
    𐰇
    0.43
    Atlantic
    0.42
    POSITIVE LOGITS
     sehr
    0.45
     يج
    0.44
     spezif
    0.44
    href
    0.44
     omin
    0.43
    上的
    0.42
    ichte
    0.42
     عليك
    0.42
     бойынша
    0.42
     lidt
    0.42
    Activations Density 0.000%

    No Known Activations