© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19998
    Prev
    Next
    INDEX
    Explanations

    petal, tulip, ventricle, Petunia

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

    This neuron identifies plant and anatomical terms, particularly focusing on "petal" and "ventricle" words.

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

    The neuron strongly activates on occurrences of “petal” (and its forms) in botanical contexts.

    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
     vernac
    -2.72
     glyphicon
    -2.59
     PROBLE
    -2.52
    ﻂ
    -2.50
     latine
    -2.50
     appartement
    -2.50
    ꯸
    -2.50
     tomba
    -2.45
     maniere
    -2.45
     luci
    -2.45
    POSITIVE LOGITS
    '
    2.67
     
    2.58
     the
    2.42
     veremos
    2.27
    .''
    2.22
     realizando
    2.16
     buscando
    2.14
     Other
    2.14
     ``
    2.11
     TABLE
    2.09
    Activations Density 0.004%

    No Known Activations