© 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. 161770
    Prev
    Next
    INDEX
    Explanations

    foreign languages or technical terms

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

    travel itinerary

    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
    ера
    0.52
    푼
    0.47
    ин
    0.44
    ле
    0.43
    俶
    0.43
    кол
    0.42
    і
    0.42
    ен
    0.42
    λε
    0.42
    清楚
    0.42
    POSITIVE LOGITS
    USSR
    0.56
     ব্যবস্থা
    0.50
     অসহ
    0.50
    VING
    0.48
    வினை
    0.48
     午前
    0.47
    Waste
    0.47
     чуде
    0.47
     effluents
    0.47
    Heating
    0.47
    Activations Density 0.000%

    No Known Activations