© 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. 68486
    Prev
    Next
    INDEX
    Explanations

    foraging, forage, or porridge

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

    The neuron strongly activates on words related to foraging (forage, forager, foraging) and associated feeding contexts.

    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
    鹀
    -2.89
    饪
    -2.89
    嗩
    -2.53
    埽
    -2.52
    umerable
    -2.50
    ઁ
    -2.48
    龶
    -2.44
    Ꮸ
    -2.44
    蚰
    -2.44
    蔀
    -2.39
    POSITIVE LOGITS
    e
    3.03
    x
    2.78
    —
    2.33
    ?
    2.28
    Y
    2.27
     These
    2.23
     produce
    2.20
     for
    2.16
     is
    2.14
    s
    2.14
    Activations Density 0.004%

    No Known Activations