© 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. 16007
    Prev
    Next
    INDEX
    Explanations

    streaming services or modern frustrations

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

    The neuron fires most strongly on the first real word that begins each new paragraph (i.e. paragraph-initial tokens).

    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
    .
    0.82
    experience
    0.79
    *
    0.77
     *
    0.75
    เวณ
    0.73
    ,
    0.73
    /
    0.71
    ’
    0.70
    ل
    0.68
     “
    0.65
    POSITIVE LOGITS
     apiKey
    0.91
    GLISH
    0.87
    佶
    0.86
     celtic
    0.86
    াইয়৷
    0.83
    బాద్
    0.82
     antice
    0.81
     coeffs
    0.80
     AssetImage
    0.80
     américains
    0.79
    Activations Density 0.000%

    No Known Activations