© 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. 15917
    Prev
    Next
    INDEX
    Explanations

    launches, announces, or offers

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

    The neuron strongly activates on tokens that are part of titles or labels—especially capitalized names, trademarks, product or brand names, and numerical or date-like tokens.

    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
     हमको
    1.17
    私たちの
    1.13
    我们需要
    1.08
     আমাদেরকে
    1.05
    我们的
    1.02
     tivemos
    1.02
     nosso
    1.02
     нашу
    1.02
    给我们
    1.02
     chúng
    1.01
    POSITIVE LOGITS
    ™.
    0.73
     www
    0.71
    ™,
    0.68
    *$
    0.67
     באמצעות
    0.65
     consumers
    0.65
    *,
    0.65
     ¬
    0.64
     Available
    0.63
    也可
    0.63
    Activations Density 0.355%

    No Known Activations