© 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. 36354
    Prev
    Next
    INDEX
    Explanations

    regex patterns

    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
     +
    0.45
    O
    0.42
    。
    0.42
    +\
    0.40
    LaTeX
    0.40
    Horizontal
    0.40
    化
    0.39
    apping
    0.39
    Digits
    0.39
     écart
    0.39
    POSITIVE LOGITS
     weddings
    0.47
    asshi
    0.46
     eclectic
    0.46
     ava
    0.45
     strugg
    0.44
     festivals
    0.44
     結婚
    0.44
    udarstven
    0.43
    -【
    0.43
     sts
    0.43
    Activations Density 0.017%

    No Known Activations