© 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. 7276
    Prev
    Next
    INDEX
    Explanations

    foreign language Wikipedia articles

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

    The neuron mainly fires on numeric tokens, especially floating‐point or other multi‐digit number strings.

    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
    um
    0.87
    OM
    0.85
    に
    0.82
    t
    0.81
    UM
    0.80
    dis
    0.79
    ur
    0.79
    te
    0.79
    ])
    0.79
    UR
    0.78
    POSITIVE LOGITS
     Wikipédia
    1.23
     YouT
    1.17
     Vikipedi
    1.14
     YouTube
    1.13
     Découvrez
    1.03
     Wikipedia
    1.02
     特許庁
    1.00
     гэта
    1.00
     Außerdem
    0.98
     cairan
    0.96
    Activations Density 0.225%

    No Known Activations