© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3089
    Prev
    Next
    INDEX
    Explanations

    in SAP, React, Python, etc

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

    The neuron specifically fires on mentions of “charity” or human acts of charity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ใคร
    0.57
     saudara
    0.57
    어
    0.57
    nesday
    0.57
     Jimin
    0.55
     Atlet
    0.54
     Davide
    0.54
     Hobbit
    0.54
    ]，
    0.54
    ปี
    0.53
    POSITIVE LOGITS
     which
    0.98
    which
    0.82
     accordance
    0.75
     relation
    0.73
     perpetuity
    0.67
     contexts
    0.66
     conjunction
    0.64
     которых
    0.63
     pursuance
    0.63
     based
    0.62
    Activations Density 0.292%

    No Known Activations