© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94191
    Prev
    Next
    INDEX
    Explanations

    licenses and registrations

    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
    rentino
    -0.83
    ņem
    -0.69
    forall
    -0.69
     映
    -0.68
     Funding
    -0.67
     step
    -0.66
    PrintWriter
    -0.66
     Seren
    -0.65
     seid
    -0.65
     Kig
    -0.65
    POSITIVE LOGITS
    cheidung
    0.67
     Leather
    0.66
     collaborators
    0.65
    目次
    0.65
    Здесь
    0.63
    Everyday
    0.62
     umur
    0.62
     disruptive
    0.61
    Sobre
    0.61
     settlers
    0.61
    Activations Density 0.103%

    No Known Activations