© 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. 6846
    Prev
    Next
    INDEX
    Explanations

    PHP action forms

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

    The neuron lights up on words that signal actions or states in procedural/technical contexts—things like “added,” “request,” “availability,” “stock,” “preparing,” and “update.”

    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
    PROBLEM
    0.91
    మ
    0.81
    黝
    0.79
    INTRO
    0.74
    LEAR
    0.74
    TIL
    0.72
    ULTURE
    0.70
    בש
    0.70
    GRAD
    0.69
    BURSEMENTS
    0.69
    POSITIVE LOGITS
    y
    1.15
    e
    1.11
    k
    1.02
    t
    0.91
    punch
    0.84
    nk
    0.83
    tm
    0.82
     Niet
    0.82
     maggiori
    0.82
    a
    0.82
    Activations Density 0.000%

    No Known Activations