© 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. 253041
    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
     целью
    0.52
    皐
    0.50
    具体的な
    0.49
     రచన
    0.49
     σχετικά
    0.47
    neutrophiles
    0.46
    dincer
    0.46
    録
    0.46
     പഠ
    0.46
    贛
    0.45
    POSITIVE LOGITS
     buoy
    0.57
     another
    0.54
    0.54
    +
    0.53
     ll
    0.52
     four
    0.52
     curved
    0.51
    4
    0.50
     other
    0.50
     less
    0.50
    Activations Density 0.004%

    No Known Activations