© 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. 260307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Geschäfts
    0.50
     Balkan
    0.50
    ా
    0.45
    規則
    0.44
    と思う
    0.44
     kto
    0.43
     Todor
    0.42
     Интернет
    0.42
    "，
    0.42
    コア
    0.41
    POSITIVE LOGITS
    <
    0.57
    ::<
    0.55
    typeparam
    0.52
    generic
    0.46
     <
    0.45
    neux
    0.44
    zoic
    0.44
     مخصوص
    0.42
     generic
    0.42
    <(),
    0.42
    Activations Density 0.001%

    No Known Activations