© 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. 142234
    Prev
    Next
    INDEX
    Explanations

    foreign language linguistics

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

    Analytics, history, effect, architecture

    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
    يه
    0.53
     ciclos
    0.53
     derechos
    0.52
    ੀ
    0.49
    CHI
    0.49
     RIGHTS
    0.49
     clots
    0.48
     consumables
    0.48
    يمه
    0.47
    ﺮ
    0.47
    POSITIVE LOGITS
     Ull
    0.49
    lık
    0.49
     Utrecht
    0.48
    linien
    0.46
    owntown
    0.46
     obvious
    0.44
    larına
    0.44
     kie
    0.44
     безо
    0.43
    ตำแหน่ง
    0.42
    Activations Density 0.000%

    No Known Activations