© 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. 73478
    Prev
    Next
    INDEX
    Explanations

    express.static usage

    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
     baca
    -0.91
     Ukrainian
    -0.89
    Zobacz
    -0.85
    КС
    -0.84
    Ucraina
    -0.82
     cinta
    -0.80
     bero
    -0.79
     Romanian
    -0.78
     ENGLAND
    -0.77
    การ
    -0.76
    POSITIVE LOGITS
     PEST
    0.93
     juke
    0.91
     LoL
    0.89
     Mv
    0.87
     bureaus
    0.86
     swirling
    0.85
    ירת
    0.85
     CUC
    0.83
     hoes
    0.82
     footed
    0.81
    Activations Density 0.002%

    No Known Activations