© 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. 59568
    Prev
    Next
    INDEX
    Explanations

    words or less

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

    trained on

    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
    экс
    0.50
    क्र
    0.45
    。
    0.43
    淑
    0.42
    нтип
    0.41
    ါ
    0.40
    ಳೆಯ
    0.39
    [];
    0.39
    车站
    0.39
    ъм
    0.39
    POSITIVE LOGITS
     çar
    0.44
    </h2>
    0.44
    redo
    0.43
    izz
    0.41
    iritto
    0.40
    דיה
    0.39
     tira
    0.39
    seh
    0.39
    reflect
    0.38
     fondament
    0.38
    Activations Density 0.000%

    No Known Activations