© 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. 25620
    Prev
    Next
    INDEX
    Explanations

    university and specific terms

    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
     kēia
    0.44
     fibrils
    0.42
     fibr
    0.39
    로는
    0.38
     imag
    0.37
    醝
    0.37
     φορά
    0.37
    acies
    0.36
     crem
    0.36
     있을
    0.36
    POSITIVE LOGITS
    ૭
    0.43
     университета
    0.42
    ٧
    0.40
    يها
    0.40
    AMA
    0.40
    university
    0.39
    Walk
    0.38
     geçti
    0.38
    ত্রী
    0.38
     университет
    0.38
    Activations Density 0.000%

    No Known Activations