© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76387
    Prev
    Next
    INDEX
    Explanations

    coach, trainer, coaching

    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
     exams
    -0.80
     Explor
    -0.77
     snorkeling
    -0.75
    fertigung
    -0.73
     Exams
    -0.73
     majoring
    -0.71
    Exams
    -0.70
     prosecuting
    -0.69
    ņi
    -0.68
     skiers
    -0.68
    POSITIVE LOGITS
     coach
    3.47
     coaches
    3.20
     coaching
    3.20
     trainer
    2.64
    coach
    2.63
     coached
    2.56
     Coach
    2.55
    Coach
    2.48
     trainers
    2.47
    coaching
    2.42
    Activations Density 0.033%

    No Known Activations