© 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. 53575
    Prev
    Next
    INDEX
    Explanations

    you publishing or performing

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

    code syntax 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
    ᑉ
    0.50
     mehrerer
    0.49
     prerogative
    0.48
     unik
    0.48
     vulnerability
    0.48
     wygląda
    0.47
     finiteness
    0.47
     কয়েকটি
    0.46
    alih
    0.46
     costituito
    0.46
    POSITIVE LOGITS
    sell
    0.46
     продав
    0.43
    ="${
    0.43
    чу
    0.41
    ση
    0.41
    όν
    0.41
     трудо
    0.40
     ছাপা
    0.40
    eslint
    0.40
    InvariantCulture
    0.40
    Activations Density 0.000%

    No Known Activations