© 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. 22-GEMMASCOPE-RES-131K
    7. 130412
    Prev
    Next
    INDEX
    Explanations

    The neuron identifies appeals or calls for support and contributions (e.g. “donation,” “support,” “help,” “feedback,” “signature”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    making donations or contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.14
     using
    -1.05
     requires
    -1.02
    אם
    -1.00
    பு
    -1.00
    telefon
    -1.00
    Њ
    -0.97
    🧺
    -0.97
    –¿
    -0.97
    其
    -0.96
    POSITIVE LOGITS
     help
    1.47
     giúp
    1.26
     sayesinde
    1.13
    help
    1.07
     باعث
    1.07
    神
    1.00
    atrician
    1.00
     hôm
    0.98
     umož
    0.98
    ଙ
    0.98
    Activations Density 0.020%

    No Known Activations