© 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. 10782
    Prev
    Next
    INDEX
    Explanations

    some and others

    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
    2
    0.54
     эти
    0.52
     on
    0.50
     واضح
    0.50
     these
    0.49
    /
    0.48
     or
    0.48
     therefore
    0.46
     one
    0.46
     этих
    0.45
    POSITIVE LOGITS
    i
    0.57
    a
    0.54
     tantos
    0.49
    ي
    0.47
    ները
    0.46
     csak
    0.44
     merely
    0.44
    colgroup
    0.43
     tantas
    0.43
    চ্ছুক
    0.43
    Activations Density 0.007%

    No Known Activations