© 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. 88896
    Prev
    Next
    INDEX
    Explanations

    multi-language fragments

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

    code structure plan

    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
    ÇA
    0.50
    🥢
    0.48
    滿足
    0.47
    ΤΑ
    0.46
    ρικ
    0.46
    ᴾ
    0.45
    🥯
    0.45
    ريك
    0.45
    瀉
    0.44
    CLUDES
    0.44
    POSITIVE LOGITS
    ag
    0.55
    mera
    0.46
     trait
    0.46
    ine
    0.46
    ug
    0.45
     solidar
    0.45
    ැනි
    0.45
    deki
    0.44
    inée
    0.44
     चयनित
    0.44
    Activations Density 0.000%

    No Known Activations