© 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. 224785
    Prev
    Next
    INDEX
    Explanations

    providing services or building

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

    system configuration aspects

    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
    。
    0.46
    λ
    0.42
    ግ
    0.41
    ⸝
    0.41
    out
    0.40
    ку
    0.40
    爆
    0.40
    с
    0.40
    undred
    0.39
    hObject
    0.39
    POSITIVE LOGITS
     suatu
    0.54
     सेवा
    0.52
     konfigur
    0.50
     آسیب
    0.50
     utilización
    0.49
     სისტ
    0.49
     sistem
    0.49
     वास्तु
    0.49
     سیستم
    0.48
     시스템
    0.47
    Activations Density 0.001%

    No Known Activations