© 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. 9371
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on discrete category or classification labels (e.g. Macro, Micro, demographical, Political/Economic/Social/Technological/Environmental, moderate, isometric, rehabilitative, etc.).

    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
    ARRANT
    0.66
    atzeko
    0.65
     ong
    0.64
     featuring
    0.63
    anik
    0.62
     stared
    0.60
     calibre
    0.60
    ')):
    0.59
     ড
    0.59
     Sw
    0.59
    POSITIVE LOGITS
    匏
    0.64
    这也是
    0.59
     אותו
    0.56
    जिसे
    0.55
    一股
    0.55
    祝
    0.55
     котором
    0.54
    のを
    0.54
     التاس
    0.54
     तौर
    0.54
    Activations Density 0.002%

    No Known Activations