© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12528
    Prev
    Next
    INDEX
    Explanations

    less than or equal to

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

    The neuron strongly activates on numeric tokens containing decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    sequences of digits and special characters typical of academic citations and DOI references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language indicating provision, sourcing, or coming upon something, especially in generic appreciative comments.

    oai_token-act-pair · gpt-5Triggered 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
    檚
    0.91
     EBIT
    0.85
     Provo
    0.85
     prácticas
    0.84
     quadrature
    0.84
     HMRC
    0.82
    ᱨ
    0.82
     HttpServer
    0.82
     conda
    0.81
     perceptual
    0.81
    POSITIVE LOGITS
    a
    1.16
    an
    1.13
    j
    1.11
    k
    1.09
    i
    1.07
    im
    1.06
    к
    1.02
    at
    0.96
    t
    0.95
    l
    0.94
    Activations Density 0.001%

    No Known Activations