© 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. 108373
    Prev
    Next
    INDEX
    Explanations

    reported speech speaker identifier

    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
    ibuya
    0.45
     এতটাই
    0.41
    of
    0.40
     мою
    0.39
    ⓪
    0.39
    otted
    0.39
     inductance
    0.38
    antai
    0.38
    degrees
    0.38
    lega
    0.38
    POSITIVE LOGITS
     yksi
    0.51
     the
    0.49
     an
    0.47
     one
    0.47
    ஒரு
    0.47
     inny
    0.46
    耺
    0.46
     bleiben
    0.46
    了一个
    0.46
    ছিলাম
    0.46
    Activations Density 0.007%

    No Known Activations