© 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-262K
    7. 25273
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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_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
    。《
    0.47
    );//
    0.46
     ه
    0.46
     tých
    0.46
    。「
    0.45
    ون
    0.44
    嗎
    0.44
     किरणों
    0.43
    кета
    0.42
    璈
    0.42
    POSITIVE LOGITS
    d
    0.50
    abby
    0.45
    ുമ്പോൾ
    0.44
    𝚒
    0.44
     curators
    0.43
    dal
    0.43
     Quy
    0.42
    fficient
    0.42
    s
    0.42
     include
    0.41
    Activations Density 0.057%

    No Known Activations