© 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. 89015
    Prev
    Next
    INDEX
    Explanations

    embroidered, diagram, Pak, friendships, friendship, isolates

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

    languages and concepts

    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
    s
    0.53
     lutego
    0.46
    ক্ষণ
    0.46
     begrij
    0.46
     чуть
    0.45
    honia
    0.45
     перебу
    0.44
    iej
    0.44
    sberg
    0.44
     закры
    0.44
    POSITIVE LOGITS
    چے
    0.53
    モ
    0.50
     resolves
    0.47
     soluciones
    0.47
     روشنی
    0.46
    ای
    0.45
    न्
    0.44
     friendships
    0.44
     isolates
    0.43
     friendship
    0.42
    Activations Density 0.001%

    No Known Activations