© 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. 90745
    Prev
    Next
    INDEX
    Explanations

    person defined by action or quality

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

    The neuron fires on evaluative adjectives and descriptors that rate ability or quality (e.g. “strong,” “expert,” “good,” “hard‐working,” “quick,” “successful”).

    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
     concevoir
    -1.09
     parcourir
    -1.00
     prévoir
    -1.00
     המק
    -0.94
     réduire
    -0.92
     écrire
    -0.90
     Predicate
    -0.90
     permettre
    -0.90
    şu
    -0.90
     décrire
    -0.89
    POSITIVE LOGITS
     eaters
    1.45
     dancers
    1.42
     swimmers
    1.41
     drinkers
    1.36
     dancer
    1.30
     singers
    1.28
     thinkers
    1.26
     shooter
    1.24
     performers
    1.23
     travelers
    1.22
    Activations Density 0.119%

    No Known Activations