© 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. 259683
    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
    älte
    0.50
    étaient
    0.46
     falsely
    0.45
    鹅
    0.44
     rupp
    0.44
     χ
    0.43
    SO
    0.43
     advisable
    0.43
    feb
    0.42
    前端
    0.42
    POSITIVE LOGITS
    گیرد
    0.52
    न
    0.47
     deter
    0.47
     crackdown
    0.46
    म्
    0.46
    мся
    0.46
    нить
    0.45
    цията
    0.45
    ු
    0.45
    ция
    0.44
    Activations Density 0.001%

    No Known Activations