© 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. 253694
    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
     стратеги
    0.49
     законода
    0.48
    চনা
    0.47
     чет
    0.47
    త్మిక
    0.47
     διαφορε
    0.47
    মতী
    0.45
     丶
    0.45
    籶
    0.45
    arında
    0.45
    POSITIVE LOGITS
    *
    0.59
    로
    0.55
    Is
    0.54
     risulta
    0.52
    1
    0.51
    Waar
    0.48
    Referencias
    0.47
    Título
    0.47
    Total
    0.47
    IMC
    0.47
    Activations Density 0.000%

    No Known Activations