© 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. 29017
    Prev
    Next
    INDEX
    Explanations

    possession of product or entity

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

    The neuron is activated by the third-person singular pronouns “it” and especially “its.”

    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
     Terkait
    -1.86
    rašymas
    -1.80
    什么呢
    -1.75
    Berat
    -1.70
    Şi
    -1.69
     estí
    -1.67
    Gön
    -1.66
    Tür
    -1.66
    keterangan
    -1.66
    𐍆
    -1.65
    POSITIVE LOGITS
    as
    2.06
    a
    2.06
    from
    2.06
    >
    2.00
     to
    2.00
    f
    1.79
    le
    1.69
    h
    1.65
    to
    1.64
    by
    1.64
    Activations Density 0.040%

    No Known Activations