© 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. 244781
    Prev
    Next
    INDEX
    Explanations

    family and reputation

    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
     Diagnose
    0.46
     Pritchard
    0.46
    ванных
    0.45
     Hock
    0.43
    M
    0.43
     Hic
    0.43
    점에서
    0.42
    데
    0.41
    الس
    0.41
     Server
    0.41
    POSITIVE LOGITS
    ociety
    0.54
    osil
    0.50
     रोमांटिक
    0.47
    oš
    0.46
     propriétés
    0.46
     खाद्य
    0.46
     архі
    0.45
     बौद्ध
    0.45
     роман
    0.45
     indifer
    0.45
    Activations Density 0.001%

    No Known Activations