© 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. 67490
    Prev
    Next
    INDEX
    Explanations

    abundant

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

    The neuron strongly activates on the adjective “abundant.”

    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
    ᚔ
    -3.05
     decidedly
    -2.97
    𓁹
    -2.92
    屛
    -2.86
     Quando
    -2.84
    ⻬
    -2.73
    𖣔
    -2.72
     intertw
    -2.66
     delightfully
    -2.64
    狲
    -2.64
    POSITIVE LOGITS
    Without
    3.13
    Using
    3.02
    '
    2.97
    Just
    2.95
     emphasizes
    2.88
     nearing
    2.84
    翾
    2.80
    Even
    2.75
    ஂ
    2.73
    just
    2.72
    Activations Density 0.009%

    No Known Activations