© 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. 19350
    Prev
    Next
    INDEX
    Explanations

    coaches, Nielsen, guys

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

    actions and capabilities

    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
    ahanga
    0.47
    ures
    0.45
     牛
    0.45
    itories
    0.44
    azes
    0.44
     重要
    0.44
     나오는
    0.42
    uring
    0.42
    TEMPLATE
    0.42
     வேற
    0.42
    POSITIVE LOGITS
     وتح
    0.50
     Indic
    0.49
    च
    0.48
     Armand
    0.47
    ค์
    0.47
     Leitung
    0.46
     Tric
    0.46
     đặt
    0.46
    ஊ
    0.46
    बाट
    0.46
    Activations Density 0.000%

    No Known Activations