© 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. 5606
    Prev
    Next
    INDEX
    Explanations

    section headers

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

    The neuron fires on uppercase job‐posting section headings (e.g. DUTIES, EDUCATION, EXPERIENCE, QUALIFICATIONS).

    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
    adito
    0.69
    久し
    0.67
    𝗷
    0.66
    youtu
    0.65
    followlike
    0.63
     aşk
    0.62
    ższ
    0.60
    𝗮
    0.60
     شباب
    0.59
    𝗔
    0.59
    POSITIVE LOGITS
    க்கள்
    0.65
     which
    0.64
     threatened
    0.61
     endangering
    0.60
    /
    0.60
     които
    0.58
     Authorities
    0.57
    Couldn
    0.56
     Regime
    0.56
     வகைகள்
    0.56
    Activations Density 0.001%

    No Known Activations