© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13761
    Prev
    Next
    INDEX
    Explanations

    return or industry

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

    order type after trigger

    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_16k_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
    ügen
    0.42
    ú
    0.40
    ♊
    0.40
     һәм
    0.39
    !.
    0.39
     других
    0.39
     /></
    0.38
     коммуна
    0.38
    玩家
    0.38
     বণিক
    0.38
    POSITIVE LOGITS
    ćeg
    0.44
     stessi
    0.43
     alguno
    0.42
     নিজ
    0.42
    雖
    0.42
     slightest
    0.42
     využ
    0.41
    当該
    0.41
    selves
    0.41
    লাম
    0.41
    Activations Density 1.171%

    No Known Activations