© 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. 234515
    Prev
    Next
    INDEX
    Explanations

    foreign language numbers and punctuation

    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
    還要
    0.51
     Pois
    0.50
     Extra
    0.47
     Design
    0.46
     Dist
    0.45
     Skills
    0.44
     Sitio
    0.43
    з
    0.43
     Ass
    0.42
     Sod
    0.42
    POSITIVE LOGITS
     biểu
    0.45
     اتب
    0.45
     மனதில்
    0.45
     pilotes
    0.45
     หลัก
    0.43
     เดิม
    0.43
    を行い
    0.43
     conducir
    0.43
    云计算
    0.42
     갤럭시
    0.42
    Activations Density 0.001%

    No Known Activations