© 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. 163808
    Prev
    Next
    INDEX
    Explanations

    surfacing surfaces

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

    tap

    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
    ા
    0.60
     приложение
    0.57
    вропей
    0.57
    ాన్
    0.53
    LEE
    0.53
     రిడి
    0.52
    ULTURE
    0.52
     упра
    0.52
     клетки
    0.52
    емой
    0.51
    POSITIVE LOGITS
    so
    0.56
    ↵↵
    0.52
    bo
    0.50
    i
    0.50
    pillars
    0.49
     the
    0.47
    pillar
    0.47
    ↵↵↵↵
    0.46
     analyzes
    0.46
     so
    0.44
    Activations Density 0.001%

    No Known Activations