© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129222
    Prev
    Next
    INDEX
    Explanations

    year ranges

    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
     later
    -1.06
    その後
    -1.02
     afterwards
    -1.02
     danach
    -0.99
     afterward
    -0.92
     luego
    -0.91
     composição
    -0.90
     thereafter
    -0.90
     agents
    -0.88
     anschließend
    -0.86
    POSITIVE LOGITS
     financières
    0.93
     ovarian
    0.85
    ViewModels
    0.84
    ADORES
    0.84
     légales
    0.82
    EQUALS
    0.81
    Smaller
    0.81
    ?}",
    0.81
    şiv
    0.81
     traditionnelle
    0.81
    Activations Density 0.011%

    No Known Activations