© 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. 674
    Prev
    Next
    INDEX
    Explanations

    impact of

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

    The neuron detects abstract nouns that denote significance or impact (e.g., “impacts,” “significance,” “importance,” “effects”).

    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
    드를
    0.57
    드가
    0.49
    IRD
    0.48
    bir
    0.47
    드
    0.47
    드는
    0.46
    <0x98>
    0.46
    तो
    0.46
    Temple
    0.46
    Philadelphia
    0.45
    POSITIVE LOGITS
     of
    0.85
     ofthe
    0.76
     của
    0.75
     των
    0.74
     của
    0.73
    ของการ
    0.70
     thereof
    0.68
    ของ
    0.65
     hereof
    0.62
     differences
    0.60
    Activations Density 0.000%

    No Known Activations