© 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. 39991
    Prev
    Next
    INDEX
    Explanations

    diagonal grid

    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
     fabs
    0.49
    商
    0.49
     popularly
    0.49
     forecasted
    0.49
     commercially
    0.49
     COMMERCIAL
    0.48
     coined
    0.47
     demanded
    0.47
     parrots
    0.46
    )²
    0.45
    POSITIVE LOGITS
    ین
    0.53
    да
    0.50
     एकदा
    0.47
    था
    0.46
    اني
    0.46
    انی
    0.45
     इससे
    0.43
     ближе
    0.42
    顿时
    0.41
    kadang
    0.41
    Activations Density 0.002%

    No Known Activations