© 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. 30283
    Prev
    Next
    INDEX
    Explanations

    accidental and unintentional events

    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
    ما
    0.55
     it
    0.53
     in
    0.49
    υσ
    0.49
     rechte
    0.47
    রাশ
    0.46
    টা
    0.46
    ট
    0.45
     கேள்வி
    0.45
    ভাষা
    0.44
    POSITIVE LOGITS
     unintentionally
    1.20
     inadvertently
    1.03
     accidentally
    1.01
     случайно
    1.01
     unwittingly
    1.01
     unintentional
    0.99
     unintended
    0.97
     involunt
    0.97
     inadvert
    0.96
     accidental
    0.86
    Activations Density 0.048%

    No Known Activations