© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3264
    Prev
    Next
    INDEX
    Explanations

    suffix

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

    The neuron primarily detects numeric tokens (numbers, including multi‐digit and decimal sequences).

    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
     ἡ
    0.76
     GaAs
    0.67
     Česk
    0.65
    ๑
    0.65
    ᆹ
    0.65
     ὁ
    0.64
     VEGF
    0.64
    🔖
    0.63
     FGFR
    0.62
    ۶
    0.62
    POSITIVE LOGITS
     Jr
    0.58
     -
    0.56
    Id
    0.56
    sequently
    0.56
    ouflage
    0.55
     dioxide
    0.54
     nd
    0.54
    Saver
    0.54
     Affairs
    0.52
     watchers
    0.52
    Activations Density 0.586%

    No Known Activations