© 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. 43729
    Prev
    Next
    INDEX
    Explanations

    nourish, raise, rest

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

    The neuron fires on words (including in other languages) that mean “to raise,” “lift up,” or “nourish” (e.g. raise, raising, nourish, perked up, поднять).

    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
    <
    -1.76
    elerik
    -1.74
    x
    -1.69
    .
    -1.67
     Wasn
    -1.66
     them
    -1.66
    ;
    -1.66
     Earlier
    -1.65
     Damn
    -1.63
    Они
    -1.63
    POSITIVE LOGITS
     ſta
    2.02
    鞫
    1.95
    ܆
    1.87
    笵
    1.84
    ︲
    1.83
    decoración
    1.73
    failing
    1.70
    荑
    1.68
     fabricants
    1.66
     femininas
    1.66
    Activations Density 0.001%

    No Known Activations