© 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. 105747
    Prev
    Next
    INDEX
    Explanations

    found this

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

    positive, calorie-dense, humane, slowest

    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
    ﺭ
    0.47
     بدون
    0.46
    امر
    0.46
    مر
    0.45
     বৈধ
    0.44
     و
    0.44
     табли
    0.44
     مطلق
    0.44
    గాలు
    0.43
    نيا
    0.43
    POSITIVE LOGITS
    h
    0.49
     Aquí
    0.48
     {
    0.46
     얘
    0.45
    a
    0.45
     fün
    0.44
    अ
    0.44
     tuve
    0.44
    该
    0.43
    您
    0.43
    Activations Density 0.001%

    No Known Activations