© 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. 73887
    Prev
    Next
    INDEX
    Explanations

    exercise testing

    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
    psychiat
    -1.09
     Psychiatric
    -1.02
    Psychiat
    -1.01
     цар
    -0.95
    皈
    -0.90
     psychi
    -0.89
     psychiatric
    -0.87
    taught
    -0.85
    ificação
    -0.85
     Psychiatry
    -0.82
    POSITIVE LOGITS
     athletes
    1.39
     elite
    1.37
     athlete
    1.30
     sport
    1.29
     coaches
    1.25
     Sport
    1.13
     Physiol
    1.13
     bout
    1.11
     Athletes
    1.06
    Sport
    1.04
    Activations Density 0.382%

    No Known Activations