© 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. 117625
    Prev
    Next
    INDEX
    Explanations

    medical treatments and procedures

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

    medical procedures and treatments described in clinical or promotional contexts.

    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
    味付け
    -1.05
     стихотво
    -0.99
    -0.94
     flavorful
    -0.91
     rétro
    -0.90
    bled
    -0.89
    estión
    -0.89
    ַח
    -0.88
     meningitis
    -0.88
    meldung
    -0.88
    POSITIVE LOGITS
     sessions
    1.80
     session
    1.70
     treatment
    1.68
     patients
    1.59
     results
    1.53
     procedure
    1.36
     treatments
    1.33
     clients
    1.31
     Patients
    1.26
    session
    1.23
    Activations Density 0.041%

    No Known Activations