© 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. 7049
    Prev
    Next
    INDEX
    Explanations

    numerical values with units

    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
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.52
     you
    -1.37
    atürk
    -1.35
     in
    -1.34
    😫
    -1.29
    💙
    -1.27
    😩
    -1.27
     should
    -1.27
    🤍
    -1.26
    🥹
    -1.24
    POSITIVE LOGITS
    CHREIB
    1.41
     Handeln
    1.26
     Geschenk
    1.24
    during
    1.23
    cómo
    1.22
    allows
    1.20
     футболка
    1.20
    ționale
    1.20
    provide
    1.20
     abbiamo
    1.20
    Activations Density 0.011%

    No Known Activations