© 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. 84362
    Prev
    Next
    INDEX
    Explanations

    possessive across languages

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

    The neuron flags specialized terminology—brand or model names, materials, and technical spec tokens (e.g. “Talalay,” “Dunlop,” “3 G,” “LTE,” “4 G”).

    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
     thậm
    -1.34
    sibles
    -1.32
    甚至
    -1.28
     needed
    -1.24
     segni
    -1.22
     близь
    -1.20
    iredo
    -1.20
    artement
    -1.20
    inine
    -1.20
     отвечает
    -1.20
    POSITIVE LOGITS
     you
    1.80
     your
    1.78
     or
    1.66
     شما
    1.54
     traktor
    1.52
     आपके
    1.45
     вам
    1.30
     сахара
    1.27
     kategor
    1.23
     apartament
    1.23
    Activations Density 0.050%

    No Known Activations