© 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. 154104
    Prev
    Next
    INDEX
    Explanations

    country/currency identifiers

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

    price differences, Microsoft ecosystem, stages

    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
    us
    0.57
    is
    0.56
    as
    0.51
    at
    0.50
    i
    0.49
     Your
    0.46
    syllabus
    0.46
     UPSC
    0.46
    드
    0.46
    ي
    0.45
    POSITIVE LOGITS
     غلط
    0.46
     می‌باشد
    0.45
    ்க்
    0.45
     می‌کند
    0.44
    正確
    0.44
    邏
    0.43
    ある
    0.43
     oblige
    0.43
     ወቅ
    0.43
     ألمانيا
    0.43
    Activations Density 0.001%

    No Known Activations