© 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. 254256
    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
     asp
    0.43
    <0xE3>
    0.42
     neu
    0.42
    rect
    0.42
    翘
    0.42
    len
    0.41
    汉
    0.40
    醉
    0.40
     hat
    0.39
    dom
    0.38
    POSITIVE LOGITS
    Yes
    0.55
     entrambi
    0.55
     Vocês
    0.55
     nhưng
    0.54
    ılarak
    0.52
     nên
    0.52
    ."'
    0.52
    न्ग
    0.50
    ‚¬
    0.50
     تقسيم
    0.50
    Activations Density 0.000%

    No Known Activations