© 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. 34-GEMMASCOPE-RES-131K
    7. 64636
    Prev
    Next
    INDEX
    Explanations

    negative impacts and limitations

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

    The neuron spotlights adjectives and adverbs that convey the intensity or severity of medical symptoms (e.g., trivial, severe, disabling, acute, chronic).

    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
     bruises
    -0.97
    cus
    -0.88
     will
    -0.86
     menghadapi
    -0.82
    žu
    -0.82
     posibles
    -0.79
     injuries
    -0.79
    ickness
    -0.77
    glm
    -0.77
     deaths
    -0.75
    POSITIVE LOGITS
     interfere
    2.19
     interfering
    2.02
     interferes
    1.95
     interference
    1.73
     interfered
    1.72
     impair
    1.66
     Interference
    1.59
    interference
    1.57
     impact
    1.56
     disrupt
    1.52
    Activations Density 0.129%

    No Known Activations