© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101569
    Prev
    Next
    INDEX
    Explanations

    email addresses and identifiers

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

    email addresses, particularly the '@' symbol and domain names in email format.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron spotlights sequences of digits and related punctuation (e.g. numeric literals, percent‐encodings, IP‐style 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_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
     keo
    -1.37
     heo
    -1.34
     today
    -1.30
     Chí
    -1.30
    (){
    -1.30
    emples
    -1.26
    "*
    -1.23
    茀
    -1.22
    ieke
    -1.21
    暃
    -1.21
    POSITIVE LOGITS
     Когда
    1.23
    zelfde
    1.23
     они
    1.11
     Gedanke
    1.10
     bedeut
    1.09
    Produktion
    1.09
    сля
    1.09
    Когда
    1.08
    整體
    1.07
     ciebie
    1.06
    Activations Density 0.080%

    No Known Activations