© 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. 34-GEMMASCOPE-RES-131K
    7. 102838
    Prev
    Next
    INDEX
    Explanations

    brown followed by noun

    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
    pezi
    -0.74
     táctil
    -0.67
     migli
    -0.67
     reducing
    -0.66
    pening
    -0.66
     apoya
    -0.65
    arranty
    -0.65
    Proyectos
    -0.64
    sivité
    -0.64
    omite
    -0.63
    POSITIVE LOGITS
     Agre
    0.81
    third
    0.76
    ICS
    0.75
    ⚠
    0.75
    Freedom
    0.73
    spheric
    0.73
    Jordan
    0.73
    پی
    0.72
     Leigh
    0.72
    EXE
    0.72
    Activations Density 0.107%

    No Known Activations