© 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. 129925
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
     toujours
    -0.92
     moldes
    -0.86
     dzies
    -0.86
    ticale
    -0.85
     ansiedad
    -0.85
    気がします
    -0.84
     tiendas
    -0.84
     fatiga
    -0.84
    dji
    -0.83
    irci
    -0.83
    POSITIVE LOGITS
     other
    0.94
     also
    0.89
     both
    0.81
     these
    0.80
     further
    0.79
    other
    0.78
     diğer
    0.77
    ございます
    0.74
     first
    0.71
    以外の
    0.70
    Activations Density 0.098%

    No Known Activations