© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82815
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
     between
    -0.84
    <i>
    -0.83
     just
    -0.78
     from
    -0.78
     Opening
    -0.78
     in
    -0.75
    oría
    -0.74
     virker
    -0.74
     câteva
    -0.74
    Opening
    -0.73
    POSITIVE LOGITS
     offici
    1.06
     services
    1.02
     service
    0.94
     graves
    0.90
    躊
    0.89
     ingrediente
    0.89
     kiin
    0.85
    Giveaway
    0.84
     noon
    0.83
     douleurs
    0.83
    Activations Density 0.001%

    No Known Activations