© 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. 84857
    Prev
    Next
    INDEX
    Explanations

    submitted dates and locations

    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
     werewolf
    -0.82
     жо
    -0.78
    requestFocus
    -0.71
     KF
    -0.70
     KV
    -0.68
    tikel
    -0.68
     hooves
    -0.68
     Leaven
    -0.67
     Fordham
    -0.67
     slippery
    -0.66
    POSITIVE LOGITS
    لے
    0.79
     Radford
    0.77
    Ashe
    0.76
    چھ
    0.75
     Fayette
    0.73
     Pulaski
    0.73
     NC
    0.72
     perdidos
    0.71
     Ashe
    0.70
    chehen
    0.69
    Activations Density 0.028%

    No Known Activations