© 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. 128262
    Prev
    Next
    INDEX
    Explanations

    actions and processes

    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
     which
    -1.80
     its
    -1.71
     changes
    -1.66
     benefits
    -1.55
     what
    -1.45
     is
    -1.41
     ability
    -1.41
     provides
    -1.40
     advantages
    -1.38
     it
    -1.32
    POSITIVE LOGITS
     fréquemment
    1.55
    ");
    1.45
     véritables
    1.44
     églises
    1.42
    ){
    1.40
    </em>
    1.40
     tão
    1.38
     nettement
    1.34
     utilizzare
    1.33
     déclarations
    1.33
    Activations Density 0.140%

    No Known Activations