© 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. 620
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

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

    This neuron detects markup tags (e.g. HTML/UBB “<div…>” quote‐block elements).

    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
    ência
    0.31
    érateur
    0.31
     καὶ
    0.30
    drž
    0.29
     Ψ
    0.29
     Faça
    0.28
    érieures
    0.28
    ÉRI
    0.28
    Ι
    0.28
    stituto
    0.28
    POSITIVE LOGITS
     as
    0.29
    as
    0.25
    if
    0.24
    <unused63>
    0.24
     according
    0.24
     during
    0.22
    ,
    0.22
     in
    0.22
     despite
    0.21
    ↵
    0.21
    Activations Density 0.000%

    No Known Activations