© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5779
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions

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

    The neuron activates on hedging or qualifying words—terms that express negation, uncertainty, or absolute qualification (e.g. “not,” “always,” “unsure,” etc.).

    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
    ());
    0.96
    .);
    0.94
    》。
    0.93
     );
    0.88
    >();
    0.85
    》,
    0.85
    );
    0.84
     ).
    0.84
    "/>.
    0.84
    »).
    0.83
    POSITIVE LOGITS
     (!)
    0.89
    (!)
    0.88
    !]
    0.71
    !,
    0.66
     unbek
    0.65
     supremely
    0.65
     albeit
    0.64
     appunto
    0.64
    !()
    0.64
    !-
    0.64
    Activations Density 0.364%

    No Known Activations