© 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. 7360
    Prev
    Next
    INDEX
    Explanations

    baseline comparisons

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

    This neuron primarily detects numeric expressions and statistical measurements (e.g., counts, percentages, confidence intervals).

    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
    厚生
    0.55
    謐
    0.55
     disproportion
    0.52
     obtained
    0.52
     collaborations
    0.52
     suitable
    0.51
    обще
    0.51
     registers
    0.51
    是个
    0.51
     qualifies
    0.51
    POSITIVE LOGITS
     placebo
    1.08
     Gruppe
    1.02
     grupo
    0.98
    Gruppe
    0.95
     그룹
    0.94
     группе
    0.93
    组
    0.93
    組
    0.93
    グループ
    0.92
     GROUP
    0.89
    Activations Density 0.169%

    No Known Activations