© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15003
    Prev
    Next
    INDEX
    Explanations

    collection

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

    string literals or quotes

    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_16k_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
     ضرور
    0.54
    케
    0.49
    Զ
    0.48
    Zr
    0.47
    گر
    0.46
     डायबिटीज
    0.45
    鮨
    0.44
    را
    0.44
    这类
    0.44
    ﻧ
    0.44
    POSITIVE LOGITS
    ull
    0.49
     fragment
    0.46
    ised
    0.45
    ikan
    0.45
     Tanah
    0.44
    ιασ
    0.43
     juli
    0.42
     Frederick
    0.42
     British
    0.42
    ész
    0.42
    Activations Density 0.001%

    No Known Activations