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. 124995
    Prev
    Next
    INDEX
    Explanations

    BOL (e.g., BOLIVIA)

    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
    zó
    0.49
    ന്തര
    0.45
    触摸
    0.44
     Leu
    0.42
    净
    0.41
    沺
    0.40
     lượt
    0.40
     Robo
    0.40
    倌
    0.40
    <0xED>
    0.39
    POSITIVE LOGITS
    BL
    0.44
     aggressiveness
    0.40
     акы
    0.40
    yi
    0.39
    one
    0.39
    really
    0.39
     subscript
    0.39
     affective
    0.38
    逆に
    0.38
    Definitely
    0.38
    Activations Density 0.015%

    No Known Activations