© 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. 255017
    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
    黐
    0.52
     सर्वाधिक
    0.51
    itett
    0.50
     بتوان
    0.50
    就已经
    0.47
    richtungen
    0.47
     चौथा
    0.46
     चलना
    0.46
    ကျော်
    0.46
     نروح
    0.46
    POSITIVE LOGITS
    }
    0.56
     agricultural
    0.46
    н
    0.45
    RA
    0.45
    "},
    0.43
    뮐
    0.43
     replaced
    0.42
    IPE
    0.42
     tubules
    0.42
     QUILL
    0.41
    Activations Density 0.000%

    No Known Activations