© 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. 10147
    Prev
    Next
    INDEX
    Explanations

    use to promote

    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
     boks
    -1.73
     kabel
    -1.72
    ſtion
    -1.68
     広場
    -1.66
     Octobre
    -1.59
     简约
    -1.59
     amerik
    -1.58
     brune
    -1.57
    ĭ
    -1.52
     suisse
    -1.52
    POSITIVE LOGITS
     to
    3.17
     
    1.96
     -
    1.84
    ;
    1.70
    ?
    1.64
     of
    1.58
     |
    1.53
    !
    1.49
    s
    1.49
     In
    1.48
    Activations Density 0.035%

    No Known Activations