© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117110
    Prev
    Next
    INDEX
    Explanations

    training and learning

    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
     Planner
    -0.70
    SCIENCE
    -0.70
     dynamite
    -0.70
    textField
    -0.70
     caribe
    -0.69
    gnancy
    -0.68
     SCIENCE
    -0.68
     labi
    -0.67
    Nord
    -0.66
    belts
    -0.66
    POSITIVE LOGITS
     training
    2.02
     Training
    1.52
    Training
    1.39
     trainer
    1.34
    training
    1.34
     TRAINING
    1.27
     trainers
    1.21
    训练
    1.17
     instructors
    1.16
     instructor
    1.10
    Activations Density 0.025%

    No Known Activations