© 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. 259317
    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
    愚
    0.52
    语文
    0.52
    akarane
    0.50
    靳
    0.48
    文本
    0.47
     Vergangenheit
    0.46
    fromj
    0.46
    ∋
    0.46
     leyenda
    0.46
     comulti
    0.45
    POSITIVE LOGITS
    in
    0.71
    l
    0.62
     $\%$
    0.47
     use
    0.47
    use
    0.46
    л
    0.46
     state
    0.45
     build
    0.44
     switch
    0.44
     lovely
    0.44
    Activations Density 0.000%

    No Known Activations