© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10921
    Prev
    Next
    INDEX
    Explanations

    <h1> tag followed by login or content

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

    The neuron strongly activates on system error messages (e.g. “Oops, something wrong happened, please try again”).

    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
    }[(
    0.60
     уйнау
    0.57
    >',
    0.56
     аз
    0.53
     >=
    0.52
     Operated
    0.51
     hashedPassword
    0.51
     어려
    0.50
    ллин
    0.50
    HeaderText
    0.50
    POSITIVE LOGITS
    ينية
    0.58
     jus
    0.56
    طاء
    0.54
    ائدة
    0.54
     Jahn
    0.54
     rela
    0.52
    胿
    0.52
     दूध
    0.52
     Harwell
    0.52
     Poole
    0.52
    Activations Density 0.000%

    No Known Activations