© 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-65K
    7. 49192
    Prev
    Next
    INDEX
    Explanations

    character, persona, or role

    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_65k_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
    ব
    0.94
    ك
    0.85
    س
    0.84
    た
    0.83
    ح
    0.80
    ক
    0.79
    ने
    0.78
    ज
    0.76
    ス
    0.75
    ING
    0.75
    POSITIVE LOGITS
     Character
    0.92
     Characters
    0.82
     Charakter
    0.80
     characters
    0.75
    Character
    0.75
     karakter
    0.75
    ى
    0.75
     personnages
    0.71
     وكانت
    0.71
    Characters
    0.71
    Activations Density 0.081%

    No Known Activations