© 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. 22-GEMMASCOPE-RES-131K
    7. 129845
    Prev
    Next
    INDEX
    Explanations

    types and methods

    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_22/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
     őket
    -1.07
    ouvre
    -1.02
    spod
    -0.97
     moż
    -0.96
     onları
    -0.95
     ľah
    -0.95
     explicó
    -0.94
    ።
    -0.94
     uiteindelijk
    -0.94
    getCurrent
    -0.93
    POSITIVE LOGITS
     viera
    0.99
     when
    0.94
     if
    0.94
    Cuándo
    0.94
    Everything
    0.90
    More
    0.89
     hanya
    0.89
     sockaddr
    0.88
     dejo
    0.88
    metall
    0.88
    Activations Density 0.040%

    No Known Activations