© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10167
    Prev
    Next
    INDEX
    Explanations

    dark matter and dark energy

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

    The neuron strongly activates on the very first content word at the start of a new text segment or paragraph.

    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
     Diocese
    0.87
    ির
    0.80
    俠
    0.79
    ㎖
    0.78
     denominations
    0.78
     beneficiaries
    0.77
     ordnance
    0.76
     handicapped
    0.75
     инициа
    0.75
     способствует
    0.75
    POSITIVE LOGITS
    }$}
    0.81
    िक
    0.77
    G
    0.73
    ظهر
    0.71
    ام
    0.70
    AM
    0.69
    パクト
    0.69
    ic
    0.66
    7
    0.66
    प
    0.65
    Activations Density 0.000%

    No Known Activations