© 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. 71958
    Prev
    Next
    INDEX
    Explanations

    case study

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

    The neuron consistently fires on occurrences of the phrase “case study.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    -2.11
    ;
    -1.95
     The
    -1.94
    ')
    -1.88
    
    -1.73
     ว่า
    -1.73
    辚
    -1.71
     การ
    -1.70
    }
    -1.70
    ครื่อง
    -1.66
    POSITIVE LOGITS
     of
    2.28
    s
    1.93
     másik
    1.80
              
    1.80
     để
    1.77
    することも
    1.77
    鸯
    1.70
    :
    1.68
    尔的
    1.67
                                   
    1.63
    Activations Density 0.006%

    No Known Activations