© 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. 209059
    Prev
    Next
    INDEX
    Explanations

    SLS comments train half-marathon

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

    find flight or restaurant

    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
    ב
    0.50
    도
    0.49
    ຜະລິດຕະພັນ
    0.48
    ா
    0.47
     errichtet
    0.46
    হোক
    0.46
    ाह
    0.46
     anisot
    0.46
    ⚌
    0.46
     Lankan
    0.45
    POSITIVE LOGITS
    igne
    0.48
     calam
    0.47
     lightning
    0.46
    room
    0.44
    billed
    0.44
     परीक्षाओं
    0.43
    screen
    0.43
    recyclerview
    0.42
     नेक
    0.42
    submenu
    0.42
    Activations Density 0.000%

    No Known Activations