© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70801
    Prev
    Next
    INDEX
    Explanations

    amplifier configuration, variable gain

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

    The neuron detects technical specification tokens—especially numbers, hyphens, and alphanumeric part/model identifiers (e.g. “Op-amp LT60…,” “–”), as used in electronics documentation.

    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
     mensen
    -1.82
    ﻷ
    -1.80
     السياس
    -1.66
     it
    -1.60
     мамы
    -1.56
     représentants
    -1.53
     бампер
    -1.51
     cuatro
    -1.51
    showed
    -1.50
    พูด
    -1.49
    POSITIVE LOGITS
     with
    2.20
     hidupnya
    1.81
    ଷ
    1.70
     narkoba
    1.63
     illustratie
    1.59
     Since
    1.54
     الجلد
    1.54
     at
    1.52
     as
    1.51
     before
    1.50
    Activations Density 0.465%

    No Known Activations