© 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. 34-GEMMASCOPE-RES-131K
    7. 118148
    Prev
    Next
    INDEX
    Explanations

    getting worse or bigger

    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_34/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
    loginButton
    -0.90
    suche
    -0.85
    Biblioteca
    -0.81
     candidats
    -0.80
     Cách
    -0.80
    comparable
    -0.79
    lahir
    -0.79
    卫生间
    -0.79
     meubles
    -0.78
    ῞
    -0.78
    POSITIVE LOGITS
     stronger
    2.70
     bigger
    2.66
     richer
    2.48
     brighter
    2.41
     louder
    2.36
     larger
    2.25
     taller
    2.23
     better
    2.23
     thicker
    2.16
     darker
    2.14
    Activations Density 0.052%

    No Known Activations