© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73069
    Prev
    Next
    INDEX
    Explanations

    subfamily classification

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

    The neuron detects biological taxonomy rank terms (e.g. family, subfamily, tribe, genus) in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -2.09
     on
    -1.89
     a
    -1.83
     polícia
    -1.65
    </b>
    -1.64
     cantora
    -1.59
     as
    -1.55
     for
    -1.52
    []{"
    -1.48
     "
    -1.48
    POSITIVE LOGITS
     épar
    1.89
    lahraga
    1.88
     différentes
    1.72
    accueil
    1.66
     écl
    1.66
     déchets
    1.63
     tiroirs
    1.61
     dégâts
    1.59
    齮
    1.56
    rógeno
    1.55
    Activations Density 0.115%

    No Known Activations