Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39184
    Prev
    Next
    INDEX
    Explanations

    questions starting with who

    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
    on
    0.39
     récupération
    0.39
    न
    0.39
     गुणों
    0.39
    ㄞ
    0.39
    ום
    0.39
    nCount
    0.39
     செயல்படுத்த
    0.38
    値
    0.38
    重量
    0.38
    POSITIVE LOGITS
     Who
    0.84
    Who
    0.84
     who
    0.83
     siapa
    0.80
    who
    0.78
    whom
    0.72
     whom
    0.71
    Кто
    0.70
     хто
    0.70
    谁
    0.70
    Activations Density 0.060%

    No Known Activations