© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22714
    Prev
    Next
    INDEX
    Explanations

    programming language functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggac
    0.40
    Υ
    0.39
    glBind
    0.38
    ladesh
    0.37
    電気
    0.36
    akkhand
    0.36
    brar
    0.35
    ૃહ
    0.35
    kut
    0.35
    褐色
    0.35
    POSITIVE LOGITS
     hottest
    0.43
     mockery
    0.42
     média
    0.41
     አይደ
    0.41
     honoring
    0.41
     deno
    0.41
     е
    0.41
     suburbs
    0.40
     অনুসারে
    0.40
     medie
    0.39
    Activations Density 0.055%

    No Known Activations