© 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. 258845
    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
    ܝܢ
    0.54
    ಿದ
    0.53
     関
    0.50
    phoneNumber
    0.50
    ಲೂ
    0.49
    playSound
    0.47
     censored
    0.46
     debounce
    0.46
     palind
    0.46
     品質
    0.46
    POSITIVE LOGITS
    .
    0.49
     garantías
    0.40
     Selección
    0.39
     ROH
    0.38
    ানের
    0.38
     Heft
    0.37
     شیر
    0.37
    .)).
    0.37
    வற்ற
    0.37
    召开
    0.37
    Activations Density 0.001%

    No Known Activations