© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20084
    Prev
    Next
    INDEX
    Explanations

    wave-particle duality

    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
    妽
    0.46
    䤃
    0.44
    <0xA1>
    0.43
     философия
    0.42
    퇸
    0.39
    <unused981>
    0.39
     форми
    0.39
    ᱗
    0.39
     আশংকা
    0.39
    AllRef
    0.39
    POSITIVE LOGITS
     
    0.45
     spatial
    0.42
     clim
    0.39
     travels
    0.38
     days
    0.38
    ئ
    0.37
     الط
    0.36
     cells
    0.36
     jogging
    0.36
    -
    0.35
    Activations Density 0.527%

    No Known Activations