© 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. 15170
    Prev
    Next
    INDEX
    Explanations

    lights, illumination, guiding, LED

    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
    agamanam
    0.50
    гово
    0.49
    半年
    0.48
     చెప్ప
    0.47
    CHREIB
    0.47
     रचना
    0.46
    妄
    0.46
    板块
    0.46
     FormData
    0.44
    fpr
    0.44
    POSITIVE LOGITS
     lights
    1.52
     lighting
    1.50
     illumination
    1.50
     Lighting
    1.44
     iluminación
    1.40
     lamps
    1.38
     LEDs
    1.37
     illuminate
    1.34
    灯
    1.31
     illuminating
    1.30
    Activations Density 0.170%

    No Known Activations