© 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. 3238
    Prev
    Next
    INDEX
    Explanations

    family health and studies

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

    mentions of family-related organizations, institutions, or health services.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on the word immediately following “family” or “families.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     intricacies
    -0.96
     phenomenal
    -0.88
     virtually
    -0.87
     perpetually
    -0.83
     evidently
    -0.82
    خة
    -0.82
     級
    -0.81
    嬗
    -0.81
     supremely
    -0.81
     troubling
    -0.81
    POSITIVE LOGITS
    不是很
    0.81
     ATTR
    0.81
    ulation
    0.80
     Edmunds
    0.78
    gine
    0.76
    lysm
    0.76
    gungen
    0.75
     GEAR
    0.75
    AKES
    0.75
    อบ
    0.74
    Activations Density 0.045%

    No Known Activations