© 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. 119813
    Prev
    Next
    INDEX
    Explanations

    hidden gem or best choice

    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
     that
    -2.69
     then
    -1.60
     about
    -1.52
    
    -1.43
     from
    -1.42
     the
    -1.37
     portata
    -1.36
     może
    -1.33
     impresiones
    -1.28
     esigen
    -1.27
    POSITIVE LOGITS
    起来的
    1.63
    Urine
    1.41
    出了一
    1.34
    OUR
    1.30
    潦
    1.28
    掉的
    1.25
    Possui
    1.24
    谪
    1.23
     campagnes
    1.23
     ดำ
    1.23
    Activations Density 0.022%

    No Known Activations