© 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. 13291
    Prev
    Next
    INDEX
    Explanations

    instructions on code

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

    This neuron detects instances of backward-looking discourse markers referring to earlier content—most prominently the phrase “the above.”

    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
    Throwable
    0.75
     봤
    0.73
    ן
    0.73
     了
    0.71
     小物
    0.70
     ción
    0.69
     Phas
    0.69
    ל
    0.69
    雱
    0.68
    了好
    0.67
    POSITIVE LOGITS
    im
    1.01
    ci
    0.90
    is
    0.84
     attribution
    0.82
    il
    0.82
     reproach
    0.80
    ide
    0.79
    um
    0.77
    aket
    0.77
     remains
    0.77
    Activations Density 0.056%

    No Known Activations