© 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. 128137
    Prev
    Next
    INDEX
    Explanations

    was sentenced or told

    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
     também
    -1.82
     también
    -1.68
     каждого
    -1.51
     (
    -1.46
     you
    -1.41
     również
    -1.34
     också
    -1.34
    вість
    -1.26
     which
    -1.23
     about
    -1.23
    POSITIVE LOGITS
     naturen
    1.40
     kroppen
    1.33
     sidste
    1.30
     словом
    1.23
     følge
    1.23
     kürzlich
    1.23
     vrouw
    1.23
     samarbeid
    1.19
    жина
    1.19
     fredag
    1.16
    Activations Density 0.699%

    No Known Activations