© 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. 14341
    Prev
    Next
    INDEX
    Explanations

    official designation or statement

    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
     Verhält
    -1.30
     \{
    -1.30
    tação
    -1.27
     ὁ
    -1.22
     THESE
    -1.22
    鴞
    -1.21
    IonicModule
    -1.20
     architekt
    -1.17
    sizePolicy
    -1.16
     alleged
    -1.16
    POSITIVE LOGITS
    official
    1.77
     ufficiali
    1.60
     it
    1.52
    Official
    1.52
    oficial
    1.42
     officially
    1.41
     официаль
    1.40
     resmi
    1.38
     officielle
    1.38
     there
    1.37
    Activations Density 0.070%

    No Known Activations