© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85264
    Prev
    Next
    INDEX
    Explanations

    charity work and events

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

    The neuron activates on occurrences of the word “charity” (and closely associated mentions of charitable organizations).

    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
    ৢ
    -3.08
    龉
    -2.84
     admittedly
    -2.80
     was
    -2.67
    ໊
    -2.50
    佉
    -2.47
    簠
    -2.42
    龅
    -2.42
     então
    -2.41
    呿
    -2.39
    POSITIVE LOGITS
    0
    2.80
    .
    2.80
    e
    2.78
    —
    2.70
    er
    2.50
    ’
    2.48
    ...");
    2.45
    ");
    2.44
    </b>
    2.39
    --
    2.38
    Activations Density 0.003%

    No Known Activations