© 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. 16120
    Prev
    Next
    INDEX
    Explanations

    heels or sandals

    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
    apiVersion
    0.41
     Я
    0.40
    já
    0.40
     м
    0.39
     야
    0.39
    प्रे
    0.38
    形容
    0.37
     ہوئی
    0.37
     મ
    0.37
     Мария
    0.37
    POSITIVE LOGITS
    某些
    0.43
    లను
    0.43
     hinzu
    0.43
     menambahkan
    0.42
    kadot
    0.41
    슭
    0.40
    क्षेप
    0.40
     añadi
    0.39
     zentrale
    0.39
     centrales
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.