© 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. 260795
    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
    娱
    0.58
    郑
    0.52
    Bitte
    0.51
    嘏
    0.51
    娱乐
    0.51
    Revel
    0.51
    课
    0.51
    货
    0.50
    讲
    0.50
    Creo
    0.50
    POSITIVE LOGITS
     a
    0.51
     reported
    0.47
     consecutive
    0.47
     Mg
    0.45
     judgement
    0.45
     racemic
    0.45
     znám
    0.44
     pylori
    0.44
     précédente
    0.44
     citation
    0.44
    Activations Density 0.000%

    No Known Activations