© 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. 22-GEMMASCOPE-RES-131K
    7. 36133
    Prev
    Next
    INDEX
    Explanations

    expressing an option

    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
    siao
    -0.86
    borderFill
    -0.79
     Renato
    -0.75
    mml
    -0.73
    dialog
    -0.73
    等待
    -0.73
    一定是
    -0.73
    acty
    -0.72
    Charge
    -0.71
    不足
    -0.71
    POSITIVE LOGITS
     option
    1.72
     OPTION
    1.51
     optional
    1.46
     optionally
    1.41
    option
    1.35
     Option
    1.29
    optional
    1.27
    Option
    1.25
     opcional
    1.23
    OPTION
    1.22
    Activations Density 0.096%

    No Known Activations