© 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. 10-GEMMASCOPE-RES-131K
    7. 72161
    Prev
    Next
    INDEX
    Explanations

    device model names

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Efter
    -1.30
    プレイヤー
    -1.27
    Čo
    -1.27
    Ꝑ
    -1.27
    INGREDIENT
    -1.27
     profonde
    -1.26
    瘊
    -1.26
    揠
    -1.23
    蚧
    -1.23
     chiffres
    -1.20
    POSITIVE LOGITS
     there
    2.02
    .
    1.83
     every
    1.40
     of
    1.38
     for
    1.38
     is
    1.38
     eight
    1.37
     even
    1.35
     slight
    1.34
     at
    1.32
    Activations Density 0.115%

    No Known Activations