© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86830
    Prev
    Next
    INDEX
    Explanations

    people meeting or bonding

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

    The neuron fires strongly on verbs that describe people coming together—especially “met” and similar social‐encounter verbs.

    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
     with
    -1.07
     lately
    -1.05
     wraz
    -1.00
     ieri
    -0.98
     junto
    -0.95
     its
    -0.94
    辨
    -0.93
     yesterday
    -0.91
    ConstraintLayout
    -0.89
    ิลปะ
    -0.88
    POSITIVE LOGITS
     mutual
    1.85
    mutual
    1.59
    Mutual
    1.55
     courtship
    1.20
     sparks
    1.20
     Mutual
    1.17
    fate
    1.14
     mutually
    1.14
     saling
    1.09
     acquaintance
    1.08
    Activations Density 0.026%

    No Known Activations