© 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. 65809
    Prev
    Next
    INDEX
    Explanations

    exposed

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

    Systems run

    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
     الأولى
    0.52
     Yards
    0.51
    é
    0.49
    。",
    0.48
    အား
    0.48
    havi
    0.48
     Weitere
    0.47
     तैयारियों
    0.46
     বাদশা
    0.46
    yard
    0.45
    POSITIVE LOGITS
    '=
    0.45
     antibiotic
    0.44
    ܠܐ
    0.44
     HEL
    0.44
    समु
    0.43
    लर
    0.42
    ҳо
    0.42
     taver
    0.42
     investment
    0.42
     coop
    0.42
    Activations Density 0.000%

    No Known Activations