© 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. 1804
    Prev
    Next
    INDEX
    Explanations

    positive descriptors of people

    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
     ஆகியவை
    0.37
     추가
    0.35
    包含
    0.35
    ０
    0.34
     config
    0.33
    ตรวจสอบ
    0.33
     removing
    0.32
    0
    0.32
     delete
    0.32
     నమోదు
    0.31
    POSITIVE LOGITS
     charismatic
    0.52
     altijd
    0.49
     tireless
    0.49
     brilliant
    0.47
     prodigious
    0.47
     outspoken
    0.47
     талант
    0.46
     lovable
    0.46
     charisma
    0.45
     personalità
    0.45
    Activations Density 0.553%

    No Known Activations