© 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. 34-GEMMASCOPE-RES-131K
    7. 59378
    Prev
    Next
    INDEX
    Explanations

    actions following possessives

    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
    gique
    -0.90
     föruts
    -0.85
    ü
    -0.84
     проблемы
    -0.82
     contamos
    -0.81
     enjeux
    -0.77
    eliness
    -0.76
    encer
    -0.76
    сы
    -0.76
    🆃
    -0.75
    POSITIVE LOGITS
     actions
    5.91
     behavior
    4.13
    actions
    3.84
     behaviour
    3.75
    Actions
    3.61
     action
    3.50
     Actions
    3.50
     acciones
    3.25
     ACTIONS
    3.14
     behaviors
    3.05
    Activations Density 0.058%

    No Known Activations