© 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. 256607
    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
    ának
    0.49
    恴
    0.48
    ্লাস
    0.46
    ítés
    0.45
    밍
    0.45
    Quiet
    0.44
    دت
    0.44
     Schaden
    0.44
    ภาย
    0.44
     Greene
    0.43
    POSITIVE LOGITS
     woman
    0.55
     secretory
    0.49
    rophot
    0.48
     একজনকে
    0.48
    sword
    0.47
    :.
    0.47
    {#
    0.46
    thememanager
    0.46
     memutuskan
    0.46
    🌆
    0.46
    Activations Density 0.000%

    No Known Activations