© 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. 39177
    Prev
    Next
    INDEX
    Explanations

    technical concepts and data formats

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

    The neuron responds to technical programming–related nouns that name data structures or data elements (e.g. routing, structure, filenames, entry, row, table, data).

    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
     bemerkt
    -1.17
    tilization
    -1.11
     vendus
    -1.08
     funktionieren
    -1.05
     обычно
    -1.05
     ausdrück
    -1.05
     Erkrank
    -1.03
     ``
    -1.03
     {
    -1.02
     bewerten
    -1.00
    POSITIVE LOGITS
    ʂ
    1.13
    倣
    1.02
     keh
    0.96
     cio
    0.96
    〜。
    0.93
     retra
    0.93
     cose
    0.91
     sufic
    0.91
    ⽬
    0.90
     SELF
    0.90
    Activations Density 0.194%

    No Known Activations