© 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. 23925
    Prev
    Next
    INDEX
    Explanations

    Windows Phone, Seven Wonders, exceptions

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

    programming entity instantiation

    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
    ص
    0.47
     چگونه
    0.47
     اب
    0.46
     أشهر
    0.46
     دقیق
    0.43
    حو
    0.43
     অথবা
    0.43
    則
    0.42
     outbursts
    0.42
     توسط
    0.42
    POSITIVE LOGITS
    lerinden
    0.46
    <>(
    0.45
    বাংলাদেশ
    0.40
    (...
    0.39
    从
    0.39
    ();//
    0.38
     позволя
    0.38
    []{
    0.38
     प्रावधान
    0.38
    -(
    0.37
    Activations Density 0.000%

    No Known Activations