© 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. 57996
    Prev
    Next
    INDEX
    Explanations

    therapeutic action and relationship

    np_acts-logits-general · gemini-2.5-flash-lite

    academic or clinical text related to psychotherapy and psychological treatment approaches.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     courrier
    -1.09
     citroen
    -1.09
     ANNOUNC
    -1.03
     lande
    -0.95
     ORDERS
    -0.93
     Tener
    -0.92
     constater
    -0.90
     gena
    -0.90
     チェーン
    -0.88
     توسعه
    -0.88
    POSITIVE LOGITS
     client
    2.11
     clients
    2.08
     session
    1.87
     therapy
    1.84
     sessions
    1.66
     Clients
    1.65
    clients
    1.61
    CLIENT
    1.61
     therapeutic
    1.57
     Client
    1.52
    Activations Density 0.060%

    No Known Activations