© 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. 9224
    Prev
    Next
    INDEX
    Explanations

    2 followed by punctuation or list items

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

    The neuron is activated by floating‐point numeric tokens (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_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
    umptions
    0.58
    事前
    0.57
    ็บ
    0.52
     Михаил
    0.52
    ))$,
    0.52
    marital
    0.52
    圿
    0.52
    thapi
    0.51
    <0x8F>
    0.50
    abhavam
    0.50
    POSITIVE LOGITS
     best
    0.98
     BEST
    0.88
     besten
    0.87
     second
    0.83
     ebenfalls
    0.81
     SECOND
    0.77
     segunda
    0.76
    BEST
    0.74
     segundo
    0.73
     Best
    0.71
    Activations Density 0.001%

    No Known Activations