© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65963
    Prev
    Next
    INDEX
    Explanations

    fullest, slightest, abbreviated, clumsy, seeming

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

    The neuron strongly activates on superlative adjectives ending in “-est.”

    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
    i
    -3.00
    遢
    -2.73
    ꯶
    -2.61
    י
    -2.52
    い
    -2.52
    
    -2.50
    ি
    -2.47
    
    -2.45
    떳
    -2.39
    荜
    -2.38
    POSITIVE LOGITS
    "
    3.02
    '
    2.88
     of
    2.75
     entwickelte
    2.67
    lossians
    2.66
     Didn
    2.53
     that
    2.52
    that
    2.50
    ),
    2.42
     as
    2.34
    Activations Density 0.002%

    No Known Activations