© 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. 16274
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases

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

    find commands and descriptions

    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
     dated
    0.49
    ্স
    0.45
    ‌های
    0.44
    у
    0.44
    上
    0.44
     gazed
    0.44
    อร์
    0.43
    δος
    0.42
     stopped
    0.42
    ెస్
    0.42
    POSITIVE LOGITS
     capitalismo
    0.57
     ممال
    0.54
    Means
    0.53
     إل
    0.53
    𒍑
    0.50
     чет
    0.49
     جري
    0.49
     совокуп
    0.49
    lında
    0.49
    inker
    0.48
    Activations Density 0.000%

    No Known Activations