© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1516
    Prev
    Next
    INDEX
    Explanations

    given topics and introductions

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

    The neuron fires specifically on the “A:” answer marker in a Q&A transcript.

    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
     es
    0.57
     ficando
    0.55
     tehát
    0.54
    '));
    0.54
    mobile
    0.53
     pero
    0.52
     entonces
    0.52
     হইলে
    0.52
    円
    0.52
    `}
    0.52
    POSITIVE LOGITS
     Given
    1.07
    Given
    0.92
     given
    0.91
    given
    0.86
     गिवन
    0.76
     Introduction
    0.72
     주어진
    0.71
     Topic
    0.71
     Provided
    0.70
     topic
    0.69
    Activations Density 0.000%

    No Known Activations