© 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. 107312
    Prev
    Next
    INDEX
    Explanations

    dealershipflagwaitingtaskimagescommentRV

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

    expressions and inquiries

    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
    பி
    0.48
    গ্রাফ
    0.48
    算法
    0.46
    ২২
    0.45
     नुकसान
    0.44
    팁
    0.44
    বুঝ
    0.43
    卷积
    0.43
    手数
    0.43
    ।
    0.43
    POSITIVE LOGITS
     افراد
    0.46
     autonomous
    0.45
     deras
    0.44
     scheint
    0.44
     netto
    0.44
    وست
    0.43
     ihre
    0.42
    م
    0.42
    mä
    0.42
    নকে
    0.41
    Activations Density 0.003%

    No Known Activations