© 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. 34-GEMMASCOPE-RES-131K
    7. 64065
    Prev
    Next
    INDEX
    Explanations

    motivational action and behavior

    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
     개발
    -0.79
     تعريف
    -0.78
    uchtigkeit
    -0.76
    Rwanda
    -0.75
    wanan
    -0.73
     creazione
    -0.73
    EXACT
    -0.73
    וא
    -0.72
    dett
    -0.71
     खे
    -0.71
    POSITIVE LOGITS
     aroused
    1.17
     drive
    1.03
     Energ
    0.96
     motivational
    0.94
    energy
    0.92
    investment
    0.91
    energ
    0.91
     energi
    0.91
     energy
    0.91
     motor
    0.87
    Activations Density 0.080%

    No Known Activations