© 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. 19319
    Prev
    Next
    INDEX
    Explanations

    ranges and individual values

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

    variation and ranges

    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
     secondes
    0.49
    我们会
    0.45
    怸
    0.44
     ພວກເຮົາ
    0.43
    🚛
    0.42
    ামাক
    0.42
    लु
    0.42
    Goodbye
    0.41
    Transaksi
    0.41
    Przeczytaj
    0.41
    POSITIVE LOGITS
     individual
    0.50
     +/-
    0.47
     lows
    0.45
     variability
    0.45
     Dipl
    0.41
    individual
    0.41
     diplomatic
    0.41
     individually
    0.41
     ranged
    0.41
     extremes
    0.41
    Activations Density 0.029%

    No Known Activations