© 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. 2388
    Prev
    Next
    INDEX
    Explanations

    rough estimate, religion, behaviors

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

    This neuron fires most strongly on the first content word of a new topical segment—typically a salient noun or proper name marking a topic shift.

    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
    다른
    0.98
    ν
    0.84
    （
    0.84
    ”（
    0.79
     συνε
    0.79
     hủy
    0.79
     interag
    0.79
     नजदी
    0.78
     révé
    0.78
    nomin
    0.77
    POSITIVE LOGITS
     வாழ்வில்
    0.68
     włas
    0.66
     Http
    0.65
     hardy
    0.65
    ća
    0.64
     abroad
    0.64
    妣
    0.64
     pampered
    0.63
    💞
    0.63
    bedarf
    0.62
    Activations Density 0.000%

    No Known Activations