© 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. 260044
    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
     filth
    0.53
     funct
    0.46
     mucous
    0.45
    வியில்
    0.45
    日は
    0.43
    依
    0.43
     ذره
    0.42
    申込
    0.41
    職
    0.41
    ウイルス
    0.41
    POSITIVE LOGITS
     അല്ല
    0.52
     Ори
    0.45
     போல
    0.44
     δὲ
    0.43
     tehát
    0.42
    rijke
    0.42
     Segmentation
    0.42
     当前
    0.41
    ürm
    0.41
     Vermont
    0.41
    Activations Density 0.000%

    No Known Activations