© 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. 187906
    Prev
    Next
    INDEX
    Explanations

    customer service or company details

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

    situations, opinions, and communication

    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
    esimo
    0.47
     Centrale
    0.46
     Pard
    0.46
     Bren
    0.45
     Musée
    0.43
    ን
    0.43
     alebo
    0.42
     proviso
    0.42
     ಮ
    0.42
     theorem
    0.42
    POSITIVE LOGITS
    ir
    0.61
    参数向量
    0.52
     최소
    0.50
     사용
    0.47
     минима
    0.47
    蛔
    0.47
    Stew
    0.46
     يستخدم
    0.45
    IService
    0.45
    aln
    0.45
    Activations Density 0.001%

    No Known Activations