© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1781
    Prev
    Next
    INDEX
    Explanations

    from the

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

    The neuron is activated by numeric tokens, especially multi‐digit and decimal numbers.

    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_24_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
    NG
    0.58
    単
    0.54
     have
    0.53
    ID
    0.53
    RIO
    0.52
    have
    0.51
    7
    0.49
    MAC
    0.49
    DE
    0.48
    ド
    0.48
    POSITIVE LOGITS
     the
    1.27
     any
    0.97
     each
    0.96
     this
    0.93
     our
    0.92
     fhe
    0.89
     these
    0.88
     ihe
    0.86
     your
    0.84
     its
    0.84
    Activations Density 0.001%

    No Known Activations