© 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. 224056
    Prev
    Next
    INDEX
    Explanations

    ", "are", "is", "online", "MC"

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

    encouraged delays

    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
     Rwandan
    0.47
     Ralph
    0.45
    ’
    0.44
     leverage
    0.44
     রাজশাহ
    0.43
    bsen
    0.42
     Sinai
    0.42
    听说
    0.42
     Jar
    0.41
     Air
    0.41
    POSITIVE LOGITS
     форму
    0.52
    穏
    0.50
     microbe
    0.49
    динку
    0.48
     complejidad
    0.48
    恣
    0.47
     adipis
    0.47
    ન
    0.47
     vē
    0.46
     sencilla
    0.46
    Activations Density 0.001%

    No Known Activations