© 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. 166177
    Prev
    Next
    INDEX
    Explanations

    punctuation and code constructs

    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
     dirty
    0.43
     California
    0.40
     wip
    0.40
     cushion
    0.37
     Coy
    0.37
     δ
    0.37
     σκ
    0.37
     Montague
    0.36
     You
    0.36
     sitt
    0.36
    POSITIVE LOGITS
    voli
    0.42
     emphasises
    0.41
    ದಾರ
    0.40
     katva
    0.39
    getStudentNo
    0.39
     $<\
    0.38
    বনে
    0.38
    㖩
    0.38
    medi
    0.38
     होटल
    0.38
    Activations Density 0.000%

    No Known Activations