© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18675
    Prev
    Next
    INDEX
    Explanations

    describing lists, scenes, or processes

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

    command prompt navigate

    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
     خیلی
    0.40
     αποφ
    0.34
    ά
    0.34
    7
    0.34
    カスタム
    0.34
    8
    0.34
     https
    0.34
    ราคา
    0.34
    !”
    0.33
     Very
    0.33
    POSITIVE LOGITS
    representing
    0.43
    governmental
    0.43
     mammalian
    0.42
     সংসারের
    0.42
     sowohl
    0.41
    帏
    0.41
    ourent
    0.40
     zowel
    0.39
    身为
    0.38
     фоне
    0.38
    Activations Density 0.012%

    No Known Activations