© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6550
    Prev
    Next
    INDEX
    Explanations

    strange occurrences and capital gains

    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_40_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
    YA
    0.46
    CAR
    0.43
    Wt
    0.43
    Y
    0.42
    Pt
    0.41
    oche
    0.40
    uru
    0.39
    Skill
    0.39
    TAM
    0.39
     மய
    0.39
    POSITIVE LOGITS
     clippings
    0.48
     паль
    0.47
     పాట
    0.46
     ឬ
    0.46
     Tayyip
    0.43
     juxtap
    0.43
    长时间
    0.42
     vmax
    0.42
    ಙ
    0.41
     പാ
    0.41
    Activations Density 0.000%

    No Known Activations