© 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. 106840
    Prev
    Next
    INDEX
    Explanations

    spending time being somewhere

    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
     создать
    -0.83
     frowning
    -0.82
     creation
    -0.82
     also
    -0.81
     makam
    -0.79
    roidered
    -0.78
    тельство
    -0.77
     implement
    -0.77
    φέ
    -0.77
     לת
    -0.76
    POSITIVE LOGITS
     being
    2.14
     spending
    2.03
     going
    1.95
     entering
    1.80
     getting
    1.80
     attending
    1.79
     staying
    1.77
     sitting
    1.73
     visiting
    1.65
     playing
    1.63
    Activations Density 0.095%

    No Known Activations