© 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. 257673
    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
     अवस्थ
    0.52
     czynności
    0.51
    !),
    0.50
     العنوان
    0.50
     ය
    0.50
     imediat
    0.50
    ),
    0.50
     प्रार्थना
    0.49
     Kantor
    0.47
    MB
    0.46
    POSITIVE LOGITS
    渇
    0.47
    虎
    0.47
    <0x80>
    0.46
    セル
    0.45
     snake
    0.45
    ﾟ
    0.44
    遜
    0.43
    蛇
    0.43
    ”?
    0.42
    包
    0.42
    Activations Density 0.000%

    No Known Activations