© 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. 22-GEMMASCOPE-RES-131K
    7. 64387
    Prev
    Next
    INDEX
    Explanations

    recipients of

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     сайты
    -1.21
     etc
    -1.16
    两个人
    -1.13
    というか
    -1.10
    けます
    -1.02
    などが
    -0.95
    などは
    -0.95
     people
    -0.93
    几个
    -0.93
    などの
    -0.92
    POSITIVE LOGITS
     who
    2.03
     whom
    1.38
     such
    1.30
     extraordinaire
    1.26
    whom
    1.17
     that
    1.13
    ᐉ
    1.11
     Many
    1.09
     bernama
    1.08
    σουμε
    1.08
    Activations Density 0.097%

    No Known Activations