© 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. 203746
    Prev
    Next
    INDEX
    Explanations

    recommendations, orders, and luck

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

    functional system

    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
    Age
    0.47
     deemed
    0.46
     Accountability
    0.46
     resets
    0.45
    لمات
    0.45
     extrema
    0.45
    詈
    0.45
     Aging
    0.44
    पाट
    0.44
     potions
    0.44
    POSITIVE LOGITS
    kal
    0.49
    digest
    0.47
    ソフトウェア
    0.47
    software
    0.46
     کند
    0.45
     соору
    0.42
     clockRadius
    0.42
    ੫
    0.41
     ایم
    0.41
    weiß
    0.41
    Activations Density 0.001%

    No Known Activations