© 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. 22-GEMMASCOPE-RES-131K
    7. 32859
    Prev
    Next
    INDEX
    Explanations

    here are examples of

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

    This neuron fires on list‐style or how-to article headings—terms marking numbered or bulleted lists (e.g. “seven habits,” “tips,” “list of,” “five things,” “100 drones,” etc.).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     didnt
    -1.09
    tabilis
    -1.07
    unción
    -1.02
     какъ
    -1.02
     FOOTBALL
    -1.02
     AttributeSet
    -1.01
    <0xF4>
    -1.01
    Anzahl
    -1.00
    metheus
    -0.99
     BORN
    -0.98
    POSITIVE LOGITS
    </h1>
    1.11
     your
    1.09
    </h2>
    1.07
     and
    1.06
     usata
    0.88
    TEMPO
    0.87
    繋がり
    0.86
    OLIS
    0.86
     może
    0.85
    碓
    0.84
    Activations Density 0.089%

    No Known Activations