© 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. 67092
    Prev
    Next
    INDEX
    Explanations

    words like officer, presence, extent, intelligent, tags, cmd

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

    fundamentals, challenges, common, misunderstanding

    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
     “
    0.50
     Da
    0.50
    t
    0.48
     \"
    0.47
    jär
    0.47
     Nd
    0.45
     Download
    0.45
     Moss
    0.44
     Sh
    0.42
     일
    0.42
    POSITIVE LOGITS
    াইজ
    0.53
     фигур
    0.52
     संवै
    0.52
    стов
    0.51
    лева
    0.50
     swims
    0.49
    linkOpacity
    0.49
    িপ
    0.48
    িশালী
    0.48
     hiçbir
    0.48
    Activations Density 0.000%

    No Known Activations