© 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. 3329
    Prev
    Next
    INDEX
    Explanations

    describing new species

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

    scientific taxonomy and classification terms, particularly when describing new or endemic species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects formal taxonomic description phrasing—especially mentions of new species being “described” or named.

    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
    थि
    -0.88
    ogues
    -0.86
    OKAY
    -0.84
    ую
    -0.84
    ybė
    -0.83
    Warriors
    -0.81
     exprimer
    -0.81
    ANTAGES
    -0.77
     diferentes
    -0.77
    nne
    -0.77
    POSITIVE LOGITS
     taxa
    2.11
     forms
    2.05
     Forms
    1.64
     form
    1.60
    forms
    1.50
    Forms
    1.49
     taxon
    1.42
    taxa
    1.38
     формы
    1.36
    taxon
    1.27
    Activations Density 0.091%

    No Known Activations