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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9725
    Prev
    Next
    INDEX
    Explanations

    NDR Jazz, Ice run

    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
    Same
    -1.52
    t
    -1.49
     {
    -1.48
    €™
    -1.45
    AN
    -1.41
    #"
    -1.38
    //
    -1.34
    n
    -1.34
     encontre
    -1.34
    our
    -1.33
    POSITIVE LOGITS
    ectady
    1.48
    ݮ
    1.42
     musíte
    1.34
     condominio
    1.30
    泰国
    1.30
     salvación
    1.28
    tovat
    1.27
    DULE
    1.25
    ÇÕES
    1.20
    恺
    1.20
    Activations Density 0.012%

    No Known Activations