© 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. 58036
    Prev
    Next
    INDEX
    Explanations

    '''

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

    This neuron responds to Latin binomial species names (e.g. genus + species).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ţin
    -1.59
     ſuch
    -1.53
    <bos>
    -1.48
     "'
    -1.45
     Such
    -1.44
     sunflower
    -1.38
    mientos
    -1.38
     Always
    -1.37
    cellor
    -1.36
     new
    -1.35
    POSITIVE LOGITS
     tecnologias
    1.60
     when
    1.55
     it
    1.44
     aprende
    1.42
     envia
    1.42
     revelado
    1.40
     continúas
    1.39
     публика
    1.38
     możliwość
    1.37
     tarefas
    1.36
    Activations Density 0.002%

    No Known Activations