© 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. 254369
    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
     pandemia
    0.54
    アイコン
    0.48
    陥
    0.48
    ன்
    0.47
    Ǎ
    0.46
     outburst
    0.44
     ადამიან
    0.44
     signifikan
    0.43
     angered
    0.43
    ityanath
    0.43
    POSITIVE LOGITS
    🚒
    0.44
    铁路
    0.43
    ADO
    0.42
    也可以
    0.42
     tubing
    0.40
    3
    0.40
     eligibility
    0.40
     什么
    0.39
    鳝
    0.39
     轻
    0.39
    Activations Density 0.003%

    No Known Activations