© 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. 253392
    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
     ربعه
    0.38
    <unused92>
    0.38
    ؟
    0.38
     auraient
    0.38
    नगर
    0.37
     ਸੰ
    0.37
    🐙
    0.37
     อยู่
    0.37
     स्टडी
    0.37
     ﺍ
    0.37
    POSITIVE LOGITS
    1
    0.41
    ref
    0.38
    II
    0.38
     st
    0.37
     disparate
    0.37
     coping
    0.37
    e
    0.37
     “
    0.36
    U
    0.36
     examples
    0.36
    Activations Density 0.026%

    No Known Activations