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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77071
    Prev
    Next
    INDEX
    Explanations

    lighthouses and recording data

    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
    Proveedor
    0.46
    ıll
    0.43
    Estado
    0.43
    Н
    0.43
    פ
    0.43
    కుంట
    0.42
    击
    0.42
     حساس
    0.41
    unable
    0.41
     ప్
    0.41
    POSITIVE LOGITS
     kino
    0.47
     viktig
    0.45
     batik
    0.44
     treasures
    0.44
     seaport
    0.44
    涔
    0.43
    ន៍
    0.43
     belles
    0.42
     jasper
    0.41
     conseils
    0.41
    Activations Density 0.010%

    No Known Activations