© 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. 73386
    Prev
    Next
    INDEX
    Explanations

    direction and vector

    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
    mación
    -0.98
     уровня
    -0.90
    unya
    -0.85
    EQUALS
    -0.84
     bracelets
    -0.82
    ingredient
    -0.82
    byr
    -0.81
    cidos
    -0.81
     данных
    -0.80
    Bedroom
    -0.79
    POSITIVE LOGITS
     direction
    1.03
    楽しむ
    0.82
    箋
    0.81
     battu
    0.79
     directions
    0.78
     '-')
    0.77
    特定的
    0.76
    avin
    0.76
    大军
    0.76
     增加
    0.75
    Activations Density 0.029%

    No Known Activations