© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28813
    Prev
    Next
    INDEX
    Explanations

    gear tooth contact analysis

    np_acts-logits-general · gemini-2.5-flash-lite

    gears, rollers, and spheres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    甶
    0.47
    integral
    0.43
    mata
    0.43
     Phy
    0.42
     آسم
    0.41
    氙
    0.40
     "=
    0.40
    
    0.40
     burial
    0.39
     интегра
    0.39
    POSITIVE LOGITS
    齿
    0.44
    রাগ
    0.44
     dentists
    0.41
    Neigh
    0.40
    ویل
    0.40
     orthodont
    0.39
    ථා
    0.38
    abileceğ
    0.38
     Molly
    0.38
     Epsom
    0.38
    Activations Density 0.013%

    No Known Activations