© 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. 253583
    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
    事故
    0.42
     voorz
    0.42
     laughter
    0.41
    гел
    0.41
    檔
    0.40
     persen
    0.40
    fection
    0.39
    तोष
    0.39
     असंभव
    0.39
     studie
    0.39
    POSITIVE LOGITS
    ゅう
    0.52
     か
    0.49
     ব্যাপক
    0.49
     বেশকিছু
    0.48
     jih
    0.46
    ವಾಗಿರುತ್ತದೆ
    0.46
     那麼
    0.46
     ദിവസം
    0.45
     നിങ്ങളുടെ
    0.45
     め
    0.45
    Activations Density 0.007%

    No Known Activations