© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1774
    Prev
    Next
    INDEX
    Explanations

    light and illumination

    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
    agamanam
    0.45
     финансо
    0.45
    criminal
    0.44
     financeira
    0.44
    financial
    0.42
     భాష
    0.41
     financiera
    0.41
    讐
    0.41
    assapi
    0.41
    半年
    0.40
    POSITIVE LOGITS
     illumination
    1.44
     lighting
    1.41
     lights
    1.34
     Lighting
    1.33
     iluminación
    1.31
     illuminate
    1.25
     lamps
    1.23
    Lighting
    1.23
     LEDs
    1.21
     illuminating
    1.20
    Activations Density 0.209%

    No Known Activations