© 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. 11321
    Prev
    Next
    INDEX
    Explanations

    ✨ preceding words

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

    The neuron specifically responds to the label “answer,” i.e. tokens marking the answer field in a QA‐style format.

    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
     الأبيض
    0.98
    يد
    0.93
     البل
    0.87
     たり
    0.84
     δύ
    0.83
    َس
    0.82
    ید
    0.81
     तारीफ
    0.81
     Фран
    0.79
     critérios
    0.79
    POSITIVE LOGITS
    and
    0.85
    y
    0.77
     землі
    0.75
     elenc
    0.73
    esine
    0.72
    av
    0.71
     aven
    0.70
    ¡
    0.70
     intox
    0.69
    a
    0.69
    Activations Density 0.000%

    No Known Activations