© 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. 149160
    Prev
    Next
    INDEX
    Explanations

    this course of study

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

    curly braces yourself

    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
    荧
    0.42
    jpuri
    0.41
     tungsten
    0.41
     TESTING
    0.41
     тестирование
    0.40
     batalla
    0.40
    queros
    0.40
     vannak
    0.40
     pesquisa
    0.40
    띵
    0.39
    POSITIVE LOGITS
     censure
    0.46
    Constructor
    0.44
     overruling
    0.42
    而是
    0.41
     undue
    0.40
    เพื่อ
    0.39
     إلا
    0.39
    ructure
    0.39
     sondern
    0.39
     rekonstru
    0.39
    Activations Density 0.000%

    No Known Activations