© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13364
    Prev
    Next
    INDEX
    Explanations

    support and drop actions

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

    The neuron fires on words that denote possession, availability, or concealment—e.g. “hidden” or “access to.”

    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
    0.93
    og
    0.86
    uar
    0.75
    eries
    0.74
    quad
    0.72
    m
    0.71
    av
    0.71
    lli
    0.70
    eros
    0.70
    icoli
    0.69
    POSITIVE LOGITS
    SBOM
    0.80
     Selanjutnya
    0.78
    釈
    0.77
    的世界
    0.76
     coalitions
    0.75
    虽
    0.75
     вещества
    0.75
     Vegeta
    0.75
     subalgebras
    0.74
     Buffy
    0.73
    Activations Density 0.000%

    No Known Activations