© 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. 10180
    Prev
    Next
    INDEX
    Explanations

    Python slicing and code constructs

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

    This neuron activates on numeric tokens and sequences (e.g. integers, decimals, indices) in the text.

    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
     italiano
    0.52
    ®.
    0.52
     eficaz
    0.50
     Antic
    0.50
     Italy
    0.49
    蚤
    0.48
     italiane
    0.47
    និ
    0.47
    ດ້ວຍ
    0.47
    espèces
    0.47
    POSITIVE LOGITS
    :-
    1.05
    :,
    1.05
     :,
    1.03
    ::
    0.97
     :-
    0.89
    :]
    0.89
    :/
    0.84
    :])
    0.83
    :}
    0.82
     ::
    0.81
    Activations Density 0.019%

    No Known Activations