© 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. 195583
    Prev
    Next
    INDEX
    Explanations

    continuing education

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

    examples like voting

    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
    ιλ
    0.48
    ě
    0.46
    封闭
    0.46
    ب
    0.45
    可通过
    0.44
    íns
    0.44
    没办法
    0.43
    没人
    0.43
    ية
    0.42
    余裕
    0.42
    POSITIVE LOGITS
     silice
    0.49
     spectroscopy
    0.47
     Sil
    0.46
     juniper
    0.45
     spear
    0.45
     ने
    0.44
     Pah
    0.44
     Spect
    0.43
     더
    0.43
     more
    0.43
    Activations Density 0.000%

    No Known Activations