© 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. 25237
    Prev
    Next
    INDEX
    Explanations

    a grammatical structure introducing noun phrases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tarte
    -1.27
     xvii
    -1.25
     啊
    -1.16
    cibo
    -1.15
    </th>
    -1.14
     xiii
    -1.13
     heil
    -1.12
     sweter
    -1.12
    batterie
    -1.10
    crème
    -1.10
    POSITIVE LOGITS
     has
    1.28
     
    1.26
     fickle
    1.06
     expéri
    0.96
     segun
    0.95
    ᐈ
    0.93
     copi
    0.93
     padre
    0.93
     gestalten
    0.92
     on
    0.91
    Activations Density 0.039%

    No Known Activations