© 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. 34-GEMMASCOPE-RES-131K
    7. 118666
    Prev
    Next
    INDEX
    Explanations

    adjectives characterizing situations

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

    The neuron fires on descriptive adjectives conveying a strong subjective evaluation (e.g. tough, weird, hard, odd, scary).

    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
     identically
    -0.86
    XYZ
    -0.84
     веществ
    -0.82
    lación
    -0.79
    均
    -0.78
     blauw
    -0.77
    种类
    -0.77
    }`
    -0.76
    лась
    -0.76
    भी
    -0.76
    POSITIVE LOGITS
     thing
    1.88
     way
    1.57
     place
    1.27
     things
    1.24
     undertaking
    1.20
     proposition
    1.17
     accomplishment
    1.16
     addition
    1.07
     achievement
    1.07
     choice
    1.05
    Activations Density 0.045%

    No Known Activations