© 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. 116745
    Prev
    Next
    INDEX
    Explanations

    discounted tires and Printful

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

    related to specific lists

    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
    دی
    0.48
    多彩
    0.45
     بچه
    0.44
    نه
    0.43
    نگ
    0.43
    彩色
    0.43
     میخ
    0.42
    ن
    0.42
    Material
    0.42
     работы
    0.42
    POSITIVE LOGITS
     questi
    0.53
     includ
    0.50
     empres
    0.50
     discourage
    0.48
     abolish
    0.45
     diesen
    0.44
     fors
    0.44
     abolished
    0.44
     الإنترنت
    0.44
     ControllerBase
    0.43
    Activations Density 0.000%

    No Known Activations