© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13325
    Prev
    Next
    INDEX
    Explanations

    project, event, context, before, during

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

    The neuron fires on words that signal procedural or control‐flow steps—especially terms related to loops and iteration (e.g. “iteration,” “condition,” “exit,” “repeat,” “keep,” “going”).

    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_31_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
     retreats
    0.55
     учреждений
    0.52
    អេឡិចត្រូនិច
    0.51
    col
    0.51
    edal
    0.50
     ostatnich
    0.49
    Exerc
    0.48
    里
    0.47
     infrastructures
    0.47
     infraestructura
    0.47
    POSITIVE LOGITS
    这场
    1.23
     Veranstaltung
    0.96
     мероприя
    0.92
     proceedings
    0.90
    本次
    0.89
     wedstrijd
    0.88
    今回の
    0.87
    此次
    0.86
     যুদ্ধের
    0.85
    比赛
    0.83
    Activations Density 0.381%

    No Known Activations