© 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. 13532
    Prev
    Next
    INDEX
    Explanations

    reverse or opposite

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

    The neuron activates on parenthetical asides—phrases or interjections enclosed in parentheses.

    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
    injlim
    0.57
    ☒
    0.50
    accounts
    0.49
    जि
    0.47
     מיי
    0.47
    ☑
    0.47
    зня
    0.46
    𝔰
    0.46
    +++
    0.45
    ಟ್ಟ
    0.45
    POSITIVE LOGITS
     reversed
    3.64
     reverse
    3.61
     Reverse
    3.42
    Reverse
    3.42
    reverse
    3.41
    逆
    3.28
     Reversed
    3.25
    reversed
    3.23
     inverse
    3.17
     reversing
    3.14
    Activations Density 0.270%

    No Known Activations