© 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. 59745
    Prev
    Next
    INDEX
    Explanations

    code comments and file paths

    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
     可愛い
    -0.96
    fordshire
    -0.96
    ствен
    -0.93
    lograph
    -0.92
    klere
    -0.89
    titel
    -0.88
     لئے
    -0.88
    rido
    -0.88
     hermé
    -0.88
    ſtre
    -0.87
    POSITIVE LOGITS
     through
    0.94
     prominent
    0.87
     in
    0.83
    ?
    0.82
    orns
    0.81
    Recurring
    0.80
     now
    0.78
    ”
    0.77
     says
    0.77
     out
    0.76
    Activations Density 0.002%

    No Known Activations