© 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. 68081
    Prev
    Next
    INDEX
    Explanations

    is a noun state

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

    This neuron detects specialized technical or patent-style nouns (e.g. invention, device, system, signal, protocol, sequence) commonly found in formal technical specifications.

    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
    為に
    -2.19
    にします
    -1.73
     their
    -1.73
    vermectin
    -1.70
    ほうがいい
    -1.70
    corrhi
    -1.65
    carus
    -1.63
    ḿ
    -1.62
    zzet
    -1.60
    ことも
    -1.58
    POSITIVE LOGITS
     is
    4.16
     was
    3.11
    は
    2.36
     are
    2.23
     has
    2.19
    を
    1.96
    が
    1.95
     may
    1.95
    がありますが
    1.92
     could
    1.88
    Activations Density 0.807%

    No Known Activations