© 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. 233027
    Prev
    Next
    INDEX
    Explanations

    engraved front

    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
    报考
    0.48
    枧
    0.48
    招标文件
    0.46
    直线
    0.44
    复
    0.43
    쥘
    0.43
    ውን
    0.43
    远离
    0.43
    旪
    0.42
    郘
    0.42
    POSITIVE LOGITS
     opções
    0.48
    Arq
    0.48
    ELL
    0.46
     Nationwide
    0.46
    ≅
    0.46
    /
    0.46
    Quad
    0.45
    Ę
    0.45
     nationwide
    0.44
    Classe
    0.44
    Activations Density 0.000%

    No Known Activations