© 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. 94243
    Prev
    Next
    INDEX
    Explanations

    most + adjective

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

    The neuron is specially detecting occurrences of the word “most” (as a superlative/intensifier).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    があるので
    -1.17
     muitos
    -1.13
     somewhat
    -1.09
    を
    -1.06
     broader
    -1.06
    踮
    -1.05
     overall
    -1.03
     LIABLE
    -1.02
     ſi
    -1.00
    كثر
    -1.00
    POSITIVE LOGITS
     exquisite
    1.19
     incredible
    1.13
    ｪ
    1.06
     rudimentary
    1.04
     innovative
    0.99
     There
    0.97
     Trying
    0.94
    autoIncrement
    0.94
    不會
    0.92
     imaginable
    0.91
    Activations Density 0.032%

    No Known Activations