© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14401
    Prev
    Next
    INDEX
    Explanations

    glowing neon, eyes, fungus, worms

    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_40_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
     नाट
    0.46
     анато
    0.46
    HEAD
    0.42
    drying
    0.41
     تباہ
    0.40
    畄
    0.40
    侵害
    0.39
    ಚಾರ
    0.39
    <unused1809>
    0.39
    ┝
    0.39
    POSITIVE LOGITS
     glow
    1.23
     glowing
    1.09
     glows
    1.07
     Glowing
    0.93
     Glow
    0.89
    Glowing
    0.88
    glow
    0.82
     neon
    0.79
     phosph
    0.77
     luminescence
    0.73
    Activations Density 0.013%

    No Known Activations