© 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. 12904
    Prev
    Next
    INDEX
    Explanations

    technical terms or variables

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

    The neuron strongly activates on salient content words—nouns and verbs carrying the core meaning of a sentence—rather than on common function words.

    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
     remarks
    0.71
    moment
    0.70
     moment
    0.70
    ಉ
    0.65
    CI
    0.64
    йки
    0.64
    అ
    0.64
     నొప్పి
    0.63
    ప్ర
    0.63
    ports
    0.63
    POSITIVE LOGITS
     welches
    0.98
     Их
    0.93
     применения
    0.86
     их
    0.85
     أعمال
    0.82
     іх
    0.82
     باید
    0.82
     έγ
    0.82
    谐
    0.81
    ிலோ
    0.81
    Activations Density 0.000%

    No Known Activations