© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 12703
    Prev
    Next
    INDEX
    Explanations

    image you linked or sent

    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_65k_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
     asociaciones
    0.54
     difficiles
    0.50
    殡
    0.50
     conoscenza
    0.49
    CLUSIVE
    0.48
    InterfaceLine
    0.47
     منابع
    0.46
    ग्रियों
    0.46
     источники
    0.45
     asociación
    0.45
    POSITIVE LOGITS
     one
    0.49
     reward
    0.45
    ummer
    0.44
    [
    0.43
     This
    0.40
    one
    0.39
    al
    0.39
     price
    0.39
     G
    0.38
    や
    0.38
    Activations Density 0.000%

    No Known Activations