© 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. 132515
    Prev
    Next
    INDEX
    Explanations

    understanding words in multiple languages

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

    breakdown of perspectives or functions

    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
     теп
    0.49
     LOG
    0.48
    Seperti
    0.46
     плане
    0.45
    फोन
    0.44
    Cloth
    0.43
    cloth
    0.42
    দ
    0.42
    WOOD
    0.42
    ――――
    0.42
    POSITIVE LOGITS
    nze
    0.48
    renz
    0.47
     понимают
    0.46
     králov
    0.45
     později
    0.44
    ่
    0.44
     verstehen
    0.43
    ון
    0.43
    积极
    0.42
     förb
    0.42
    Activations Density 0.001%

    No Known Activations