© 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. 257409
    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
    !\
    0.49
    マン
    0.48
    鍗
    0.46
    MACl
    0.45
    員の
    0.44
    稒
    0.44
    ენტის
    0.44
    落地
    0.42
    라마
    0.42
    点の
    0.42
    POSITIVE LOGITS
     historischen
    0.53
     Couldn
    0.53
     જન્મદિવસ
    0.52
     empres
    0.48
     sendMessage
    0.48
     Dap
    0.47
     "_
    0.47
     adres
    0.47
    Adress
    0.47
    ero
    0.46
    Activations Density 0.000%

    No Known Activations