© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82652
    Prev
    Next
    INDEX
    Explanations

    available after words/things

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

    recursive ai fiction and diverse concepts

    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
    Negative Logits
    वर्तन
    0.46
    волю
    0.45
    قام
    0.45
    ות
    0.44
    ವಾದ
    0.44
    灑
    0.43
     setTodos
    0.43
    طلا
    0.43
     Investor
    0.43
    اليد
    0.43
    POSITIVE LOGITS
    4
    0.50
    afil
    0.47
     demonstration
    0.46
    ylan
    0.43
     จํา
    0.43
     चौराहे
    0.43
     demonstrations
    0.42
     jaj
    0.42
     evokes
    0.42
     रज
    0.42
    Activations Density 0.000%

    No Known Activations