© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70005
    Prev
    Next
    INDEX
    Explanations

    being followed by descriptor

    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
     but
    -1.73
     been
    -1.56
    
    -1.52
    l
    -1.51
    g
    -1.50
    romas
    -1.48
    t
    -1.48
    ations
    -1.40
     locale
    -1.39
     befolk
    -1.39
    POSITIVE LOGITS
     Também
    1.61
     Высо
    1.51
    いただきたい
    1.44
     čím
    1.40
    since
    1.37
    Also
    1.36
     étant
    1.35
    Situated
    1.34
    apore
    1.33
    お待ち
    1.32
    Activations Density 0.084%

    No Known Activations