© 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. 64588
    Prev
    Next
    INDEX
    Explanations

    concerto, lib, Saint, German, mock, Release, ns

    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
     valgt
    -1.41
     triko
    -1.34
     mieli
    -1.30
    だと思う
    -1.29
     silikon
    -1.29
     novamente
    -1.24
     DIFFERENT
    -1.21
     AGAIN
    -1.21
     mikrofon
    -1.21
     dekol
    -1.20
    POSITIVE LOGITS
    :
    1.23
     just
    1.22
     before
    1.10
    1
    1.10
     first
    1.08
    最初の
    1.07
    ・・。
    1.07
    ......
    1.06
    a
    1.06
    A
    1.05
    Activations Density 0.018%

    No Known Activations