© 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. 37477
    Prev
    Next
    INDEX
    Explanations

    creating and initializing objects

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

    programming data types

    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
    らを
    0.45
    ܒ
    0.44
     anchor
    0.43
    дон
    0.43
     לו
    0.43
     STRA
    0.42
     stek
    0.41
    ី
    0.41
     asin
    0.41
     cocktail
    0.40
    POSITIVE LOGITS
     حصول
    0.39
     chromatographed
    0.39
    AutoField
    0.38
    ilyl
    0.37
    فا
    0.36
     heralded
    0.36
     Concurrent
    0.36
     Genau
    0.36
    itaea
    0.35
    关于
    0.35
    Activations Density 0.000%

    No Known Activations