© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61710
    Prev
    Next
    INDEX
    Explanations

    sunlight or light

    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
     Rhodesia
    0.49
    百貨
    0.45
     hài
    0.43
     tendrás
    0.43
     पाएंगे
    0.43
    роятно
    0.42
     فرو
    0.41
    榈
    0.41
     ό
    0.41
     peaches
    0.41
    POSITIVE LOGITS
     components
    0.51
     performed
    0.51
    components
    0.44
     done
    0.44
     subsequently
    0.43
     non
    0.43
     lawfully
    0.43
     detected
    0.42
     previously
    0.42
     granted
    0.42
    Activations Density 0.002%

    No Known Activations