© 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. 18624
    Prev
    Next
    INDEX
    Explanations

    web links ending in .html

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

    code execution, JSON, function calls

    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
    拡張
    0.50
     specifications
    0.47
    醫
    0.46
     পাওয়ার
    0.46
    設定
    0.45
    規格
    0.45
     মেডিক্যাল
    0.45
    IV
    0.43
    毉
    0.43
    臍
    0.43
    POSITIVE LOGITS
     Ocak
    0.47
     خ
    0.45
     Ни
    0.43
     उन्ह
    0.42
    ješt
    0.41
    耸
    0.41
    ombrie
    0.40
    ></
    0.40
     dihasil
    0.40
    肨
    0.40
    Activations Density 0.001%

    No Known Activations