© 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. 153856
    Prev
    Next
    INDEX
    Explanations

    context after certain words

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

    tell me a little

    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
    nagar
    0.47
    test
    0.46
    解答
    0.45
    全世界
    0.45
    橙
    0.45
    これ
    0.45
    heath
    0.44
    بازی
    0.44
    g
    0.43
    ‪‬
    0.42
    POSITIVE LOGITS
    ľa
    0.57
     акчага
    0.53
     ಮೂ
    0.52
     terceros
    0.52
     tercero
    0.52
     পাইনি
    0.52
    Apellido
    0.50
     manque
    0.49
     акча
    0.49
     lähe
    0.48
    Activations Density 0.001%

    No Known Activations