Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16394
    Prev
    Next
    INDEX
    Explanations

    Assistant Voice

    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
     democracies
    0.56
     ecz
    0.51
     appartenant
    0.49
    颢
    0.48
    inama
    0.47
    baptism
    0.47
     prêts
    0.46
     écoles
    0.46
    ంబేద్కర్
    0.45
     renovación
    0.45
    POSITIVE LOGITS
     Man
    0.49
     S
    0.48
     Position
    0.47
     t
    0.46
     n
    0.46
     في
    0.45
    icher
    0.45
     NU
    0.45
     Tra
    0.45
     Character
    0.45
    Activations Density 0.001%

    No Known Activations