© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92117
    Prev
    Next
    INDEX
    Explanations

    spare time

    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
     gom
    -0.84
     indiquer
    -0.78
    ילום
    -0.77
    ytale
    -0.76
    gom
    -0.76
    Ϯ
    -0.76
    stattung
    -0.76
    ciety
    -0.75
    涣
    -0.75
    fade
    -0.74
    POSITIVE LOGITS
     spare
    3.61
     leisure
    3.31
     free
    2.94
     свобод
    2.52
    spare
    2.47
     downtime
    2.30
    Spare
    2.17
    free
    2.16
     Leisure
    2.14
     Freizeit
    2.08
    Activations Density 0.037%

    No Known Activations