© 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. 14085
    Prev
    Next
    INDEX
    Explanations

    questions and vulgarities

    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
     may
    0.53
     fi
    0.47
     might
    0.47
     extraordinary
    0.46
     première
    0.45
     fabulous
    0.45
     momentous
    0.44
    ،
    0.44
    いただきました
    0.43
     thoughtful
    0.43
    POSITIVE LOGITS
     idk
    0.76
     lmao
    0.73
    fuck
    0.70
     shitty
    0.68
     alot
    0.67
     fucking
    0.64
    屌
    0.63
    떄
    0.63
     fuck
    0.62
    좆
    0.60
    Activations Density 0.027%

    No Known Activations