© 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. 49422
    Prev
    Next
    INDEX
    Explanations

    to react

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

    poem about planets

    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
     Determining
    0.50
     Localization
    0.47
    歡
    0.47
    مين
    0.46
    ليس
    0.46
    tum
    0.46
     व्यंजनों
    0.45
     Getting
    0.45
    ประกัน
    0.45
     Finding
    0.44
    POSITIVE LOGITS
     diariamente
    0.50
     だ
    0.50
     جوړونکی
    0.50
     numa
    0.49
     なお
    0.47
     namik
    0.47
    earic
    0.47
    adamu
    0.45
    先に
    0.45
     täglich
    0.44
    Activations Density 0.000%

    No Known Activations