© 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. 71191
    Prev
    Next
    INDEX
    Explanations

    carve path, rumbling, radar, EN, Linear

    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
    ية
    0.57
    CONTIN
    0.55
    Gravestone
    0.49
     difficiles
    0.49
     difíciles
    0.48
    ダ
    0.48
    難
    0.48
    да
    0.47
    horizontal
    0.47
    発電
    0.46
    POSITIVE LOGITS
     extracts
    0.52
    sdl
    0.49
     pathways
    0.48
     schemas
    0.48
     serves
    0.47
    kates
    0.47
     advising
    0.46
     venues
    0.45
     pathway
    0.44
     gathers
    0.44
    Activations Density 0.001%

    No Known Activations