© 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. 38909
    Prev
    Next
    INDEX
    Explanations

    bruised colors and injuries

    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
    昅
    0.41
    bod
    0.40
    iax
    0.40
    ▇
    0.40
    精
    0.39
    launcher
    0.39
    타고
    0.39
    Arq
    0.38
     disreg
    0.37
    鬨
    0.37
    POSITIVE LOGITS
     bruises
    0.52
     bruised
    0.50
     bruising
    0.49
     bruise
    0.48
     मलया
    0.42
     Brunswick
    0.41
     ফলে
    0.40
    ют
    0.39
     luka
    0.38
    irono
    0.38
    Activations Density 0.011%

    No Known Activations