© 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. 18280
    Prev
    Next
    INDEX
    Explanations

    text visual formatting

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

    outputting with formatting

    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
    明
    0.45
    ময়
    0.45
    潙
    0.45
    一张
    0.44
    分别是
    0.44
    XZ
    0.43
    HAB
    0.43
    Geb
    0.43
    潇
    0.43
    这张
    0.43
    POSITIVE LOGITS
     शब्द
    0.49
     en
    0.45
     palabra
    0.43
     detergent
    0.41
     Frum
    0.41
     word
    0.40
     protrusion
    0.40
     jeweler
    0.39
     ).
    0.39
     Academia
    0.39
    Activations Density 0.000%

    No Known Activations