© 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. 34-GEMMASCOPE-RES-131K
    7. 91923
    Prev
    Next
    INDEX
    Explanations

    event times and broadcasts

    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
     convertView
    -0.85
     endfor
    -0.81
    🇺🇸
    -0.78
    endfor
    -0.78
     infractions
    -0.77
    频繁
    -0.76
    Togo
    -0.74
    calips
    -0.74
    ="$(
    -0.74
    two
    -0.73
    POSITIVE LOGITS
     TV
    0.95
     start
    0.91
     early
    0.86
     local
    0.84
     evening
    0.84
     traditional
    0.83
     television
    0.81
     night
    0.81
     central
    0.79
     televised
    0.79
    Activations Density 0.007%

    No Known Activations