© 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-65K
    7. 56750
    Prev
    Next
    INDEX
    Explanations

    electricity is a concept

    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
     bouts
    0.50
     verseny
    0.46
    лювання
    0.46
     sociable
    0.43
    晌
    0.41
    }~\
    0.40
    نے
    0.39
     competitiveness
    0.39
     trous
    0.39
     perspectivas
    0.39
    POSITIVE LOGITS
     Tab
    0.48
    egra
    0.46
    टी
    0.46
    Tab
    0.45
    warf
    0.45
    igui
    0.43
    推定
    0.43
    u
    0.43
     하지만
    0.42
    ΟΥ
    0.42
    Activations Density 0.028%

    No Known Activations