© 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. 7178
    Prev
    Next
    INDEX
    Explanations

    regression, linear, single

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

    The neuron fires on bracketed label words (e.g. the “Parallel” and “Counter” inside “[Parallel Flow]” and “[Counter Flow]”).

    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
    蘊
    0.70
    珵
    0.62
     चिह्न
    0.61
     Signore
    0.59
     Esperanza
    0.59
    azote
    0.58
     lawfully
    0.56
    獲
    0.56
     आधिकारिक
    0.56
    SaveChangesAsync
    0.56
    POSITIVE LOGITS
     single
    1.53
     Single
    1.48
     rectangular
    1.45
    Single
    1.40
    single
    1.39
     linear
    1.36
     SINGLE
    1.30
    SINGLE
    1.29
     monolithic
    1.29
     cylindrical
    1.27
    Activations Density 1.139%

    No Known Activations