© 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. 32679
    Prev
    Next
    INDEX
    Explanations

    filenames and identifiers

    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
     We
    -1.28
     they
    -1.25
     kann
    -1.22
     "
    -1.20
     America
    -1.15
     Can
    -1.13
     Let
    -1.13
     --
    -1.11
    it
    -1.10
     "'
    -1.10
    POSITIVE LOGITS
    Semua
    1.46
     néer
    1.42
     méd
    1.40
    Vem
    1.39
    店内は
    1.38
    蛧
    1.35
    Zdra
    1.34
    Kör
    1.34
    <bos>
    1.34
    strual
    1.32
    Activations Density 0.176%

    No Known Activations