© 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-16K
    7. 12587
    Prev
    Next
    INDEX
    Explanations

    entire or whole

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

    entire or whole

    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_16k_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
    ing
    0.75
    is
    0.71
     vogliono
    0.61
    つの
    0.61
    は
    0.60
    ampuan
    0.60
    دی
    0.59
     quieren
    0.59
     wellknown
    0.59
    Ｃ
    0.58
    POSITIVE LOGITS
    整个
    1.32
     entire
    1.20
    整個
    1.15
     Entire
    1.05
     keseluruhan
    1.01
    Entire
    0.94
    entire
    0.93
     hele
    0.90
     whole
    0.87
     पूरे
    0.86
    Activations Density 0.300%

    No Known Activations