© 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. 3643
    Prev
    Next
    INDEX
    Explanations

    radiation pressure, air forces, exponentials, DHCPv6

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

    The neuron fires on tokens that are items in a categorical list or enumeration (e.g. elements of a semicolon/comma‐separated list).

    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
     कुत्ते
    0.58
    ｙ
    0.57
     кін
    0.54
    विड़
    0.54
    ｔ
    0.54
     ನನಗೆ
    0.52
    hythmic
    0.51
    ｊ
    0.50
    linkCell
    0.49
    𝐲
    0.49
    POSITIVE LOGITS
     ஆகியவற்ற
    0.83
    ®.
    0.79
     ஆகியவை
    0.74
     รวมถึง
    0.72
    ).
    0.67
    }.
    0.63
     എന്നിവ
    0.63
     systems
    0.62
     serta
    0.62
    .
    0.62
    Activations Density 0.583%

    No Known Activations