© 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. 4050
    Prev
    Next
    INDEX
    Explanations

    elements of a list

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

    The neuron principally activates on single-word nouns denoting abstract or concrete concepts.

    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
     behem
    0.52
     bevy
    0.52
     ",
    0.51
     incluso
    0.51
    !),
    0.51
     Billion
    0.49
     Ltd
    0.48
    :
    0.48
    !",
    0.47
     god
    0.47
    POSITIVE LOGITS
    每一個
    0.61
     প্রত্যেক
    0.58
    每一
    0.57
    ம்பெ
    0.54
    㫻
    0.54
    
    0.54
    妩
    0.54
    government
    0.53
     फरवरी
    0.53
    每一个
    0.53
    Activations Density 0.001%

    No Known Activations