© 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. 50872
    Prev
    Next
    INDEX
    Explanations

    modeltechnical and list formatting

    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
    纷
    0.55
    писание
    0.53
    дание
    0.50
    FindingsRequest
    0.49
    FrameLength
    0.48
    ﺓ
    0.48
     ነገ
    0.46
    قة
    0.45
    ўні
    0.45
    ParentObject
    0.45
    POSITIVE LOGITS
     Texas
    0.52
     American
    0.48
    n
    0.45
     Federal
    0.44
     Carolina
    0.44
     mayonnaise
    0.44
     Kansas
    0.44
     Americans
    0.43
    gives
    0.43
     Alzheimer
    0.42
    Activations Density 0.003%

    No Known Activations