© 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. 22-GEMMASCOPE-RES-131K
    7. 98496
    Prev
    Next
    INDEX
    Explanations

    legal citations and names

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

    The neuron is specialized to pick out standalone underscore characters (and underscore‐based identifier tokens) used in document markup or code.

    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
     by
    -1.83
     or
    -1.55
     in
    -1.49
     you
    -1.45
    ﻷ
    -1.42
     without
    -1.41
     if
    -1.40
     before
    -1.36
     just
    -1.36
     on
    -1.36
    POSITIVE LOGITS
     Sortiment
    1.48
     Эти
    1.45
     SECRET
    1.45
    biendo
    1.44
    抠
    1.41
    嘮
    1.41
    ὺς
    1.38
     tunik
    1.34
    Елена
    1.34
    Ольга
    1.33
    Activations Density 0.000%

    No Known Activations