© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38367
    Prev
    Next
    INDEX
    Explanations

    prototype

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     "
    -2.17
    猡
    -2.14
    「
    -2.14
    that
    -2.09
    "
    -2.08
    ra
    -2.06
    -
    -2.05
     $
    -1.97
    said
    -1.95
    『
    -1.94
    POSITIVE LOGITS
     másik
    2.50
    퐹
    2.48
    镍
    2.14
     not
    2.11
    ではまた
    2.06
    硖
    2.06
    以上です
    2.05
    —”
    2.02
    冱
    2.02
     autres
    1.99
    Activations Density 0.006%

    No Known Activations