© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45635
    Prev
    Next
    INDEX
    Explanations

    family health and support

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

    references to family, family relationships, and family-related contexts.

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

    This neuron activates on occurrences of “family” (including hyphenated and derived forms like “family-based” or “familial”).

    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
     detaljer
    -0.85
    יצד
    -0.84
    ◆
    -0.80
     CONDUIT
    -0.76
     Retrieves
    -0.76
     DOMINGO
    -0.75
    newblock
    -0.75
     Galo
    -0.73
    istir
    -0.73
     revoked
    -0.73
    POSITIVE LOGITS
     stability
    0.88
     violence
    0.88
     context
    0.83
     устрой
    0.81
     unit
    0.79
    getSupport
    0.79
    Strengths
    0.79
     support
    0.78
     therapy
    0.77
     breakdown
    0.75
    Activations Density 0.039%

    No Known Activations