© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15330
    Prev
    Next
    INDEX
    Explanations

    section header

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

    This neuron detects section‐heading markers—particularly the colon following titles like “Introduction:”

    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
    И
    0.83
    Ethyl
    0.70
    百科
    0.68
    仪器
    0.65
    Ecole
    0.65
    Université
    0.64
     tror
    0.64
    Stephanie
    0.64
    Exam
    0.64
    原来的
    0.64
    POSITIVE LOGITS
    a
    0.95
    rarr
    0.77
     Premises
    0.74
    issions
    0.72
    ulai
    0.72
     LGBTQ
    0.71
     Among
    0.71
     premises
    0.71
    eking
    0.70
     Arroyo
    0.68
    Activations Density 0.000%

    No Known Activations