© 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. 22-GEMMASCOPE-RES-131K
    7. 27738
    Prev
    Next
    INDEX
    Explanations

    witnessing events, actions, or emotions

    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_22/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
     for
    -1.06
     Surveys
    -0.94
     flyer
    -0.91
    forderungen
    -0.89
    ţin
    -0.89
    att
    -0.86
     oscuridad
    -0.86
    Surveys
    -0.86
    uk
    -0.84
    cipitation
    -0.83
    POSITIVE LOGITS
     watched
    1.64
     watching
    1.42
     spectacle
    1.33
     witnessed
    1.23
    Watching
    1.23
     visible
    1.20
     observed
    1.20
     sereia
    1.16
     performed
    1.14
    watched
    1.13
    Activations Density 0.064%

    No Known Activations