© 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. 154859
    Prev
    Next
    INDEX
    Explanations

    fundamental concepts and applications

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

    fundamentals of topics

    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
    1
    0.70
    is
    0.68
    a
    0.67
    b
    0.63
    Original
    0.62
    o
    0.61
    es
    0.61
    em
    0.59
    package
    0.59
    on
    0.58
    POSITIVE LOGITS
     profesor
    0.54
     নির্বাচনের
    0.54
     treasured
    0.54
    ത്തിന്റെയും
    0.52
     révèle
    0.52
    糈
    0.51
     collaborate
    0.51
     premio
    0.51
     ช่วย
    0.50
     metodi
    0.50
    Activations Density 0.004%

    No Known Activations