© 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. 259938
    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
     జగ
    0.49
     निकले
    0.48
     экскур
    0.47
    ઉસ
    0.47
     клави
    0.47
     விரிவா
    0.46
     dolom
    0.45
    ៦
    0.44
     крепо
    0.44
    आख
    0.44
    POSITIVE LOGITS
     Birmingham
    0.45
     przyczyn
    0.42
    ffer
    0.41
    noz
    0.41
     ANY
    0.41
    ]+/
    0.40
     Certain
    0.40
     Pont
    0.39
    *)&
    0.39
     Kent
    0.38
    Activations Density 0.003%

    No Known Activations