© 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. 3997
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and formulas

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

    This neuron activates on author names and related citation tokens (e.g. initials and “et al.”) in academic‐style references.

    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
    ❣
    0.38
     zumindest
    0.37
     denominada
    0.37
     bundan
    0.37
    leitung
    0.36
    yrıca
    0.36
     répartition
    0.36
     zudem
    0.35
     edhe
    0.35
    💟
    0.35
    POSITIVE LOGITS
    for
    0.43
     can
    0.38
    lamps
    0.38
     they
    0.36
     lint
    0.36
     mornings
    0.36
    തര
    0.36
    lint
    0.35
    an
    0.35
    event
    0.35
    Activations Density 0.002%

    No Known Activations