© 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. 256587
    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
    Rightarrow
    0.43
     অধিক
    0.43
    多
    0.42
    ijska
    0.41
     অর্থ
    0.41
    成
    0.41
     عندهم
    0.40
    有一
    0.39
    ői
    0.39
     Datei
    0.39
    POSITIVE LOGITS
    ۔
    0.54
     قوانین
    0.52
     कमेटी
    0.49
    ங்களைப்
    0.48
    काल
    0.48
     lessor
    0.47
     COLE
    0.46
    Voting
    0.45
    ன்
    0.44
    คะ
    0.44
    Activations Density 0.001%

    No Known Activations