© 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. 26823
    Prev
    Next
    INDEX
    Explanations

    square units of measurement

    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
    蜘
    0.53
     fraudulently
    0.50
     pagare
    0.50
     ciudades
    0.49
    叁
    0.48
     ciudad
    0.46
     espécie
    0.46
    李
    0.45
     nè
    0.44
     afili
    0.43
    POSITIVE LOGITS
     History
    0.45
    谬
    0.43
     Comparison
    0.42
     Contrast
    0.42
    →
    0.41
     history
    0.41
     Acoustics
    0.41
     →
    0.40
    History
    0.39
     PMID
    0.37
    Activations Density 0.010%

    No Known Activations