© 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. 5477
    Prev
    Next
    INDEX
    Explanations

    Python, react, characters, rapidly

    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
    s
    0.55
    es
    0.52
    ister
    0.48
    ের
    0.46
    ège
    0.45
     شی
    0.45
    ié
    0.45
    电气
    0.45
    hz
    0.44
    is
    0.43
    POSITIVE LOGITS
    ร็จ
    0.53
    ኞ
    0.44
     CentOS
    0.43
     ሴ
    0.43
    द्र
    0.43
     Far
    0.43
    ించాలి
    0.43
     Laundry
    0.42
     Larissa
    0.42
    MovieList
    0.42
    Activations Density 0.001%

    No Known Activations