© 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. 165081
    Prev
    Next
    INDEX
    Explanations

    action or use

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

    combination of financing and LL applications

    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
    </h2>
    0.46
     Ikea
    0.45
     Propri
    0.43
     xiii
    0.43
     #
    0.42
     (
    0.41
     nas
    0.41
     »
    0.41
     begins
    0.40
     comes
    0.40
    POSITIVE LOGITS
     একইভাবে
    0.46
    र्यंत
    0.42
    忽然
    0.41
    応用
    0.40
     대상으로
    0.40
    探测
    0.40
    ເພື່ອ
    0.39
    שׁ
    0.39
     मालम
    0.39
     শ্রেণির
    0.38
    Activations Density 0.081%

    No Known Activations