© 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. 113471
    Prev
    Next
    INDEX
    Explanations

    successful kind

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

    technical or descriptive terms

    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
    斦
    0.46
     단순
    0.44
     υπάρχει
    0.43
     fixtures
    0.43
    陷入
    0.42
     가진
    0.42
    式的
    0.41
     operazioni
    0.41
    綃
    0.41
    圴
    0.41
    POSITIVE LOGITS
    ac
    0.49
     адре
    0.48
    academic
    0.46
     can
    0.46
    analytics
    0.45
    greens
    0.45
    CBD
    0.45
    モニター
    0.45
    authorised
    0.44
    ProtectedRoute
    0.44
    Activations Density 0.001%

    No Known Activations