© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5296
    Prev
    Next
    INDEX
    Explanations

    distribute and redistribute

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

    The neuron flags words about distributing or sharing content under a license (e.g., “distribute,” “freely,” “redistributes”).

    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
    𝓃
    0.75
    CE
    0.73
    STE
    0.73
    béco
    0.73
    LLOW
    0.73
    CEC
    0.73
    TON
    0.71
    TEA
    0.71
    fcast
    0.71
    TEGER
    0.70
    POSITIVE LOGITS
    اب
    0.93
     odor
    0.80
     perfumes
    0.77
    ences
    0.75
    \"\
    0.74
     क्लोरीन
    0.73
    व
    0.73
     enthal
    0.72
     this
    0.71
    ostrum
    0.71
    Activations Density 0.004%

    No Known Activations