© 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. 130823
    Prev
    Next
    INDEX
    Explanations

    your personal touches

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

    pricing level symbolism factorial

    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
    ب
    0.52
    щения
    0.50
    ه
    0.48
    ل
    0.46
    סים
    0.44
    橢
    0.44
    ثال
    0.43
    ל
    0.43
     несколь
    0.43
    核心
    0.42
    POSITIVE LOGITS
     pesante
    0.49
     rendered
    0.48
     створе
    0.46
    {|
    0.46
     jt
    0.45
     nặng
    0.45
    LGBT
    0.45
     scont
    0.45
    亀
    0.45
    (_)
    0.45
    Activations Density 0.001%

    No Known Activations