© 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. 58296
    Prev
    Next
    INDEX
    Explanations

    sensitivity to something

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

    The neuron consistently fires on the word “sensitivity” (especially when paired with numeric measures), so it flags mentions of sensitivity.

    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>
    -1.93
    gaja
    -1.92
     Alongside
    -1.83
     Create
    -1.80
    ТЫ
    -1.75
    ziek
    -1.72
     pescoço
    -1.69
    ?”
    -1.68
    воло
    -1.66
     spannend
    -1.64
    POSITIVE LOGITS
     способствует
    1.98
    where
    1.95
    镲
    1.88
    A
    1.88
     اليه
    1.85
     exposes
    1.85
    6
    1.84
    that
    1.84
     помогает
    1.79
    \
    1.79
    Activations Density 0.035%

    No Known Activations