© 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. 254643
    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
    客厅
    0.48
    谏
    0.48
    astopol
    0.46
    had
    0.46
    鄀
    0.46
    茴
    0.46
     hatte
    0.45
    등
    0.44
    äns
    0.44
     Gifford
    0.44
    POSITIVE LOGITS
     Co
    0.51
     Disease
    0.50
     IMMEDIATE
    0.50
     Mice
    0.47
     Healthcare
    0.45
     COUN
    0.45
     healthcare
    0.45
     Diseases
    0.44
     Bureau
    0.44
     Employment
    0.44
    Activations Density 0.001%

    No Known Activations