© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 191874
    Prev
    Next
    INDEX
    Explanations

    contact us

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

    cool, cooling, age, night, design

    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
    繰
    0.48
    acionales
    0.46
     gravida
    0.46
    ющие
    0.46
    ленно
    0.46
    दाताओं
    0.45
     Государ
    0.43
    Wide
    0.43
     Среди
    0.42
    :</
    0.42
    POSITIVE LOGITS
    ของการ
    0.49
     niektó
    0.49
     cools
    0.48
     COOL
    0.47
     Cooling
    0.46
     reak
    0.46
     regresa
    0.45
    istik
    0.45
     Cool
    0.44
     năng
    0.43
    Activations Density 0.001%

    No Known Activations