© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13074
    Prev
    Next
    INDEX
    Explanations

    random.rand(

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

    The neuron fires strongly on the “more” token that marks truncated content or a “read more” continuation link.

    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
    tl
    0.85
    tier
    0.83
    sulf
    0.75
    tarea
    0.75
    t
    0.75
    tv
    0.74
     important
    0.71
    tel
    0.70
     horizon
    0.69
    tedir
    0.68
    POSITIVE LOGITS
     έξ
    0.81
     conclusão
    0.80
    ^{*}=
    0.80
    하여
    0.77
     കരാ
    0.77
    ﭜ
    0.77
     προ
    0.75
    ্পনিক
    0.75
     ಈ
    0.75
     δη
    0.75
    Activations Density 0.000%

    No Known Activations