© 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. 27504
    Prev
    Next
    INDEX
    Explanations

    image source and time served

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

    task completion with parameter n

    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
     atualmente
    0.42
     здания
    0.42
     azalt
    0.41
     الاعداد
    0.41
     económ
    0.40
     الوط
    0.40
     населения
    0.39
    !("{}",
    0.39
     duración
    0.39
     actualmente
    0.38
    POSITIVE LOGITS
    formed
    0.54
    be
    0.48
    cons
    0.46
    metal
    0.45
    bir
    0.45
    being
    0.45
    fibr
    0.42
    include
    0.42
    plot
    0.42
     formed
    0.42
    Activations Density 0.000%

    No Known Activations