© 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. 68217
    Prev
    Next
    INDEX
    Explanations

    Cocoa, UIKit, macOS, frameworks

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

    The neuron fires most strongly on version-number tokens in dependency declarations (e.g. the “:x.y.z” parts of Gradle/Maven or package config lines).

    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
     stycz
    -1.29
     vivía
    -1.24
    をしました
    -1.18
     necesitaba
    -1.16
     showed
    -1.16
     seguía
    -1.16
    lsea
    -1.14
    kumpulan
    -1.14
    ospital
    -1.13
    gorra
    -1.13
    POSITIVE LOGITS
    illoma
    1.34
     모든
    1.33
    さらに
    1.27
    توضیحات
    1.22
     Dumnezeu
    1.21
    āja
    1.20
    czych
    1.19
    includes
    1.16
    ocrine
    1.14
    Included
    1.13
    Activations Density 0.010%

    No Known Activations