© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15669
    Prev
    Next
    INDEX
    Explanations

    overwhelming and complex

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

    The neuron flags non‐stopword content tokens—especially nouns and verbs that carry the core meaning in a clause (e.g. “heavy,” “poll,” “masses,” “President,” “site,” “do”).

    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
    ☺️
    0.98
    ている
    0.91
    女朋友
    0.90
    😊
    0.90
    ☺
    0.90
    Watercolor
    0.88
     Watercolor
    0.88
    😌
    0.86
    ♡
    0.84
    男朋友
    0.84
    POSITIVE LOGITS
     unwittingly
    1.20
     bureaucr
    1.19
     prolifer
    1.17
     totalitarian
    1.16
     proliferation
    1.14
     hegemony
    1.11
     uncontroll
    1.10
     orthodoxy
    1.09
     inescap
    1.08
     tyranny
    1.07
    Activations Density 2.127%

    No Known Activations