Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 916
    Prev
    Next
    INDEX
    Explanations

    convex, concave, optimization, geometry

    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_16_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
    𝙩
    0.66
    g
    0.64
    f
    0.64
    ar
    0.64
    N
    0.63
    sc
    0.60
     as
    0.60
    sh
    0.60
    v
    0.60
    re
    0.59
    POSITIVE LOGITS
     polytopes
    0.64
     Banach
    0.61
     convexe
    0.61
     foreigner
    0.60
     lipase
    0.59
     mostrou
    0.59
     savoury
    0.59
     deux
    0.58
     duas
    0.58
     trase
    0.58
    Activations Density 0.015%

    No Known Activations