© 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. 117112
    Prev
    Next
    INDEX
    Explanations

    flowing within

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

    eastward, release, force

    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
    د
    0.49
     हार्ट
    0.49
     flera
    0.48
     Heart
    0.45
     Persistent
    0.45
     flared
    0.44
    Điều
    0.43
    閪
    0.43
     tumors
    0.43
     rocky
    0.41
    POSITIVE LOGITS
    irá
    0.45
    我們會
    0.45
    imizi
    0.42
    ımızı
    0.42
     движение
    0.42
    我们要
    0.42
     نصف
    0.42
    꿨
    0.41
    enquête
    0.41
    𝓮
    0.41
    Activations Density 0.001%

    No Known Activations