© 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. 112553
    Prev
    Next
    INDEX
    Explanations

    historical institutions and events

    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
     your
    -2.17
     you
    -1.56
    signable
    -1.27
     agora
    -1.24
    already
    -1.22
                        
    -1.19
     izvē
    -1.18
     vēl
    -1.17
    yourself
    -1.16
     ļoti
    -1.15
    POSITIVE LOGITS
     decades
    1.59
     damals
    1.32
     gezwungen
    1.24
     décadas
    1.20
    чается
    1.18
     postwar
    1.13
     from
    1.13
     Fällen
    1.11
     centuries
    1.10
     ostensibly
    1.09
    Activations Density 1.341%

    No Known Activations