© 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. 90595
    Prev
    Next
    INDEX
    Explanations

    Project Tango

    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
     McCartney
    -1.42
     Beatles
    -1.40
     Liverpool
    -1.13
     beatles
    -1.08
     Liver
    -0.95
     Ringo
    -0.92
     liver
    -0.91
     LIVER
    -0.90
    Liverpool
    -0.89
    Liver
    -0.88
    POSITIVE LOGITS
     Haiti
    0.83
    Ռ
    0.78
    jast
    0.78
     Hust
    0.73
    nitts
    0.69
    zha
    0.68
     konkre
    0.68
     calculator
    0.68
    tsburgh
    0.68
    vorschau
    0.68
    Activations Density 0.007%

    No Known Activations