© 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. 165589
    Prev
    Next
    INDEX
    Explanations

    function variants

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

    code definitions and structure

    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
    锻
    0.39
    ENES
    0.39
     зай
    0.38
    zeichnen
    0.38
     могут
    0.38
     медицин
    0.38
     வெவ்வேறு
    0.38
    柞
    0.38
     персона
    0.37
     অথবা
    0.37
    POSITIVE LOGITS
     función
    0.51
     fonction
    0.46
     functie
    0.45
     Rica
    0.45
     função
    0.44
     bawa
    0.43
     funkcji
    0.42
    rrrr
    0.41
    oooooooo
    0.41
     Função
    0.40
    Activations Density 0.002%

    No Known Activations