© 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. 22-GEMMASCOPE-RES-131K
    4. 13861
    Prev
    Next
    INDEX
    Explanations

    children and family activities

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

    The neuron is strongly activated by high-frequency “stop” words—pronouns (you, them), conjunctions (and, or), prepositions (through, when, about), auxiliaries (are), etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -1.34
     should
    -1.02
     has
    -1.02
     gyven
    -1.02
     will
    -1.00
    ഖ
    -0.98
    हर
    -0.98
    panel
    -0.97
    AIDS
    -0.97
    <
    -0.96
    POSITIVE LOGITS
     kids
    2.94
     children
    2.34
     kid
    2.17
     family
    1.91
     child
    1.84
     parents
    1.84
     homeschool
    1.75
     Kids
    1.73
     families
    1.66
     toddler
    1.63
    Activations Density 0.063%

    No Known Activations