© 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-65K
    7. 3924
    Prev
    Next
    INDEX
    Explanations

    crime and code errors

    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_65k_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
     ຊ
    0.52
     일
    0.51
     واع
    0.49
    ו
    0.46
    НА
    0.46
    ИА
    0.46
     takim
    0.46
    И
    0.46
     따
    0.45
     와
    0.45
    POSITIVE LOGITS
    த்தக
    0.45
     Sentencing
    0.43
    тые
    0.41
     Moments
    0.41
     Parfum
    0.41
     stolen
    0.40
    ọng
    0.40
     Shadows
    0.40
     crimin
    0.40
    ulpt
    0.39
    Activations Density 0.012%

    No Known Activations