© 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. 13382
    Prev
    Next
    INDEX
    Explanations

    significant

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

    The neuron predominantly fires on strongly evaluative or emotionally charged words and phrases—i.e. hyperbolic adjectives and adverbs used for emphasis.

    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
     ciò
    0.60
     이는
    0.59
     ครอง
    0.57
    <unused87>
    0.57
     μή
    0.57
     것은
    0.55
     vàng
    0.55
     unruly
    0.52
    <unused65>
    0.51
     하여
    0.51
    POSITIVE LOGITS
    ’’
    0.73
    ”、
    0.73
    所有的
    0.66
    ","
    0.65
    ”“
    0.65
    "،
    0.63
    whole
    0.61
    ”،
    0.60
    ”
    0.59
     继续访问
    0.59
    Activations Density 0.020%

    No Known Activations