© 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. 41468
    Prev
    Next
    INDEX
    Explanations

    model infections

    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
    5
    0.52
    6
    0.45
    ük
    0.44
    S
    0.41
    7
    0.40
     or
    0.38
    建设
    0.38
    现状
    0.38
    คือ
    0.38
    స
    0.38
    POSITIVE LOGITS
    headers
    0.49
     makanan
    0.49
     கணி
    0.48
     resetting
    0.48
     preparando
    0.48
     বাড়ানোর
    0.48
     headers
    0.47
     omdat
    0.47
     infractions
    0.47
     वंचित
    0.46
    Activations Density 0.001%

    No Known Activations