© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226650
    Prev
    Next
    INDEX
    Explanations

    https:// URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    㞰
    0.52
     Directed
    0.50
     Voilà
    0.50
    鋈
    0.49
    嗕
    0.49
     ****",
    0.48
     opération
    0.47
    鐒
    0.47
     podľa
    0.47
     Règles
    0.47
    POSITIVE LOGITS
    up
    0.54
    erm
    0.52
    cr
    0.47
    max
    0.46
    ounds
    0.46
    ung
    0.45
     grouping
    0.45
     downgraded
    0.45
    ble
    0.44
    fe
    0.44
    Activations Density 0.002%

    No Known Activations