© 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. 22-GEMMASCOPE-RES-131K
    4. 35931
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

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

    The neuron fires on formal or technical terms—tokens that occur in bureaucratic “request for proposal” phrasing (e.g. “solicited”) or in formal specifications (e.g. the variable “N”).

    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
     this
    -1.67
     my
    -1.64
     people
    -1.59
     like
    -1.59
     someone
    -1.52
     nobody
    -1.46
     lentement
    -1.46
     not
    -1.46
     everyone
    -1.46
     I
    -1.44
    POSITIVE LOGITS
    vičius
    1.77
     السياس
    1.50
     siècles
    1.45
    θούν
    1.45
    梦见
    1.38
     viena
    1.38
     塗装
    1.38
    lesssim
    1.36
     أيام
    1.34
     "'";
    1.34
    Activations Density 0.000%

    No Known Activations