© 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. 143625
    Prev
    Next
    INDEX
    Explanations

    qualifiers and explanations

    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
     décadas
    0.52
    ți
    0.44
     decenas
    0.44
    rí
    0.44
    வரி
    0.43
     Laufe
    0.43
     seção
    0.42
    ⺊
    0.42
     नागरिकों
    0.42
    ڈ
    0.42
    POSITIVE LOGITS
     mileage
    0.43
     geographically
    0.42
     solely
    0.42
     první
    0.42
     بهذا
    0.42
     actually
    0.41
     purely
    0.41
     этими
    0.41
     logistics
    0.41
    AND
    0.41
    Activations Density 0.006%

    No Known Activations