© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70987
    Prev
    Next
    INDEX
    Explanations

    following 'of' or 'the'

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

    The neuron activates on numerical tokens (including integers and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    首先
    -1.11
     sowieso
    -1.09
    雖然
    -1.09
    其实
    -1.05
    虽然
    -1.05
    既然
    -1.05
     ktorá
    -1.04
     ešte
    -1.03
     ligh
    -1.02
    taines
    -1.02
    POSITIVE LOGITS
     a
    1.48
     also
    1.23
     such
    1.13
     an
    1.12
    ائد
    1.08
    みたいに
    1.05
     bandou
    1.05
    gilet
    1.04
     mirror
    1.04
     there
    1.04
    Activations Density 0.061%

    No Known Activations