© 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. 84018
    Prev
    Next
    INDEX
    Explanations

    substance use by students

    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
     Bengt
    -0.78
     nonverbal
    -0.73
    TRAVEL
    -0.73
    ownie
    -0.73
     prick
    -0.70
     militants
    -0.69
    УП
    -0.69
     logarith
    -0.68
     Toddler
    -0.68
     Cooler
    -0.68
    POSITIVE LOGITS
     students
    0.99
     experimentation
    0.87
     Students
    0.82
    inj
    0.82
     preco
    0.81
     risk
    0.79
    练习
    0.79
     Connected
    0.77
    Experiment
    0.75
    DataContext
    0.75
    Activations Density 0.079%

    No Known Activations