© 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. 1913
    Prev
    Next
    INDEX
    Explanations

    active participation and involvement

    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
    roasted
    -0.97
     arising
    -0.94
     alinea
    -0.93
     Vitamina
    -0.91
     facendo
    -0.90
     Aussicht
    -0.90
    limite
    -0.85
     authorizing
    -0.85
     apsau
    -0.85
     lacking
    -0.85
    POSITIVE LOGITS
    active
    1.76
     Active
    1.60
     active
    1.59
    Active
    1.56
     participation
    1.46
     actively
    1.45
     participate
    1.34
     ACTIVE
    1.30
     involvement
    1.26
     Passive
    1.22
    Activations Density 0.027%

    No Known Activations