© 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. 259010
    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
    asana
    0.50
    🪴
    0.48
    🍮
    0.48
    エネルギー
    0.47
    訃
    0.46
     formularios
    0.46
    нан
    0.46
     معاملات
    0.46
     ಮಾತ
    0.45
    ת
    0.44
    POSITIVE LOGITS
     現
    0.54
     cruisers
    0.54
     Busan
    0.51
    浠
    0.50
     OPC
    0.48
     CIRC
    0.47
     cruiser
    0.46
     races
    0.46
     silica
    0.46
     will
    0.46
    Activations Density 0.000%

    No Known Activations