© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35426
    Prev
    Next
    INDEX
    Explanations

    names followed by colons

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

    The neuron fires on numeric tokens—i.e. standalone numbers or numeric identifiers in the text.

    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
    plastik
    -1.13
    哙
    -1.10
    INCIP
    -1.09
     soggior
    -1.05
    graffiti
    -1.04
    ventajas
    -1.03
    garanti
    -1.03
    årige
    -1.03
    tissu
    -1.02
     eenen
    -1.02
    POSITIVE LOGITS
     -
    1.51
    がありますが
    1.13
     as
    1.09
     دیدار
    1.07
     in
    1.02
     ...
    1.02
    その
    1.01
     (
    0.99
    not
    0.98
    體育
    0.96
    Activations Density 0.005%

    No Known Activations