© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64864
    Prev
    Next
    INDEX
    Explanations

    normal physiological processes

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

    phrases indicating physiological or biological states in scientific texts.

    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
     cayenne
    -0.75
     Muf
    -0.75
    Studios
    -0.71
     urin
    -0.70
    Rp
    -0.69
     chinos
    -0.68
     wirken
    -0.68
    Formal
    -0.68
     Reck
    -0.68
    єї
    -0.67
    POSITIVE LOGITS
     physiological
    3.69
    physiological
    3.05
     normal
    3.05
     Physiological
    2.88
     physiologic
    2.86
    生理
    2.48
    physio
    2.41
     Physio
    2.30
    normal
    2.30
     physio
    2.28
    Activations Density 0.378%

    No Known Activations