© 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. 57204
    Prev
    Next
    INDEX
    Explanations

    foreign or multilingual contexts

    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
     unsustainable
    0.49
    उ
    0.47
     treba
    0.45
     AWAY
    0.44
     displace
    0.44
    othermic
    0.43
     ectopic
    0.43
     aHUS
    0.42
    馬上
    0.42
    উ
    0.41
    POSITIVE LOGITS
     l
    0.57
     nostru
    0.44
     Tasting
    0.44
     financières
    0.44
    馇
    0.43
     musée
    0.41
     noastră
    0.41
     нашего
    0.41
    یکه
    0.41
     françaises
    0.41
    Activations Density 0.002%

    No Known Activations