© 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. 150472
    Prev
    Next
    INDEX
    Explanations

    international competitions

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

    technical items 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
    খ
    0.49
    近平
    0.48
    电机
    0.48
    讵
    0.47
    caret
    0.47
    نڈ
    0.46
    きゃ
    0.45
    கம்
    0.44
    Textbox
    0.44
    irled
    0.44
    POSITIVE LOGITS
     Showcase
    0.49
     Story
    0.48
     organisations
    0.48
     ร่วม
    0.47
     Search
    0.47
     नगर
    0.47
     ১৪
    0.47
    .%
    0.47
     Flowering
    0.47
     Rece
    0.46
    Activations Density 0.003%

    No Known Activations