© 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. 31-GEMMASCOPE-2-RES-65K
    7. 15950
    Prev
    Next
    INDEX
    Explanations

    system, department, age, era, realm

    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_31_width_65k_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
    hluk
    0.30
     түр
    0.29
    倠
    0.27
    uris
    0.27
     مراکز
    0.26
    并发
    0.26
    㑓
    0.26
     varchar
    0.26
    ynthia
    0.26
    $^{
    0.26
    POSITIVE LOGITS
     enthalten
    0.32
     alimentare
    0.31
     Pantone
    0.29
     dorado
    0.29
     placebo
    0.29
     Fuentes
    0.29
     komme
    0.28
     Pins
    0.28
     Franks
    0.28
     cible
    0.28
    Activations Density 0.037%

    No Known Activations