© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72162
    Prev
    Next
    INDEX
    Explanations

    concepts and values

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

    the neuron detects abstract, intangible nouns denoting qualities, states, or concepts.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     efforts
    -1.61
    
    -1.52
     EXCHANGE
    -1.49
    ꪔ
    -1.46
     použí
    -1.46
     and
    -1.43
    賸
    -1.41
    幛
    -1.38
    熥
    -1.38
    楹
    -1.38
    POSITIVE LOGITS
     BOTH
    1.98
        
    1.66
     ALL
    1.59
     ALWAYS
    1.50
    </h2>
    1.48
    That
    1.47
    </h5>
    1.46
    </td>
    1.46
            
    1.45
     MOST
    1.43
    Activations Density 0.024%

    No Known Activations