© 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. 90874
    Prev
    Next
    INDEX
    Explanations

    verbs forming nouns/adjectives

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

    The neuron fires on base‐form English action verbs (e.g. inject, perform, modify, respond, examine, authorize).

    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
     Veränder
    -0.90
     namanya
    -0.89
    <h1>
    -0.88
     }),
    -0.88
    ized
    -0.87
     Beteiligung
    -0.87
    ize
    -0.85
    carol
    -0.84
    </h1>
    -0.84
    izing
    -0.81
    POSITIVE LOGITS
    able
    1.70
    ables
    1.60
    ings
    1.55
    ers
    1.41
    inge
    1.27
    outs
    1.17
    ments
    1.08
    ingly
    1.04
    heitsbild
    1.02
    ABLE
    0.97
    Activations Density 0.147%

    No Known Activations