© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39814
    Prev
    Next
    INDEX
    Explanations

    company roles

    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
     about
    -1.74
     Räume
    -1.39
    <td>
    -1.38
     only
    -1.31
     übri
    -1.30
     dergleichen
    -1.27
    और
    -1.27
    ubov
    -1.24
    ynı
    -1.23
     Zuhause
    -1.23
    POSITIVE LOGITS
     tne
    1.52
     of
    1.52
     voelt
    1.44
     pudesse
    1.23
     onderstaande
    1.23
    hawaii
    1.22
     paard
    1.20
     dochter
    1.20
    reli
    1.20
     gewel
    1.18
    Activations Density 0.078%

    No Known Activations