© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94043
    Prev
    Next
    INDEX
    Explanations

    governance terms followed by related concepts

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Reſ
    -1.50
     Homem
    -1.38
     pão
    -1.34
    )$}
    -1.27
    用に
    -1.22
     Compra
    -1.21
    ſelf
    -1.20
     repeti
    -1.20
     castelo
    -1.20
    ௅
    -1.18
    POSITIVE LOGITS
    してました
    1.50
    これも
    1.20
    してみた
    1.16
    したのが
    1.15
    させていただきました
    1.15
    していました
    1.14
    してみました
    1.13
     måte
    1.12
    طرز
    1.08
    してみると
    1.08
    Activations Density 0.515%

    No Known Activations