© 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. 184609
    Prev
    Next
    INDEX
    Explanations

    easy to cook

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

    science and industry explanations

    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
     ওয়েস্ট
    0.49
     பிரத
    0.48
     дъл
    0.48
     ब्रांड
    0.48
     Hoop
    0.47
    㒵
    0.47
     Birthday
    0.47
     اولین
    0.47
     ارزش
    0.47
    ario
    0.46
    POSITIVE LOGITS
     fleshy
    0.51
     großer
    0.46
    시에
    0.45
    t
    0.45
     zugleich
    0.44
    j
    0.44
     glandular
    0.44
     shik
    0.43
    gles
    0.43
    gery
    0.42
    Activations Density 0.000%

    No Known Activations