© 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. 58232
    Prev
    Next
    INDEX
    Explanations

    early childhood education

    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
     reading
    -0.87
     daycare
    -0.77
     db
    -0.75
    ajuku
    -0.74
     Defendant
    -0.71
     vocational
    -0.71
     preschool
    -0.71
     зрения
    -0.70
    education
    -0.69
     В
    -0.68
    POSITIVE LOGITS
    DAP
    0.97
     observes
    0.86
     DAP
    0.84
     Observing
    0.83
     Carrington
    0.83
     Modif
    0.82
     diego
    0.81
    wele
    0.79
    raciones
    0.79
    tuning
    0.78
    Activations Density 0.015%

    No Known Activations