© 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. 10-GEMMASCOPE-RES-131K
    7. 12918
    Prev
    Next
    INDEX
    Explanations

    recently, this month, Burry, Amp

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

    The neuron fires on programming‐style tokens—things like URLs to docs, file and API paths, code keywords and identifiers (e.g. CamelCase names, imports, class/func/var, GitHub repo links).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     such
    -1.63
     against
    -1.20
    Such
    -1.20
     Such
    -1.16
     podrían
    -1.13
     believed
    -1.10
     known
    -1.08
    ,
    -1.07
     péché
    -1.07
    such
    -1.05
    POSITIVE LOGITS
    鉛筆
    1.23
    :^{
    1.20
     stránka
    1.20
    ֺ
    1.19
    ἵ
    1.18
     שלך
    1.16
    ilización
    1.16
    ׇ
    1.16
    FUENTES
    1.15
     stránky
    1.14
    Activations Density 0.007%

    No Known Activations