© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    name requests

    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
     valores
    0.76
     clín
    0.73
    ب
    0.73
    ت
    0.72
     número
    0.70
     зрения
    0.69
     residuos
    0.68
    s
    0.68
                
    0.67
     gái
    0.67
    POSITIVE LOGITS
    ชื่อ
    0.87
    करण
    0.84
    name
    0.82
     name
    0.79
    names
    0.79
    ни
    0.78
     이름을
    0.78
     नाम
    0.77
    akes
    0.77
     이름
    0.75
    Activations Density 0.153%

    No Known Activations