© 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. 74203
    Prev
    Next
    INDEX
    Explanations

    planning and problem-solving contexts

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

    advertising, questions, function, FedEx

    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
     عدة
    0.46
     利
    0.46
     ラ
    0.46
     lighten
    0.45
    ](#
    0.44
     zn
    0.44
    ライト
    0.43
    利
    0.43
     विवेकानंद
    0.43
     让
    0.43
    POSITIVE LOGITS
    fungsi
    0.50
     aquilo
    0.48
     eşit
    0.47
     फंडिंग
    0.46
    οντας
    0.46
    явить
    0.45
     ஆகியவற்ற
    0.45
    sono
    0.45
    یسم
    0.45
    heng
    0.44
    Activations Density 0.000%

    No Known Activations