© 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. 127188
    Prev
    Next
    INDEX
    Explanations

    names starting with Nash or Ralph

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

    This neuron detects first- and second-person possessive pronouns (e.g. “my,” “your,” “моя,” “ваша,” etc.).

    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
    ,"
    -2.88
     musíte
    -2.41
     můžete
    -2.38
    鹮
    -2.25
    🢒
    -2.22
    䊐
    -2.19
     dwóch
    -2.16
    悫
    -2.16
    ÁG
    -2.14
    椹
    -2.14
    POSITIVE LOGITS
    (
    3.47
    r
    3.39
    h
    2.91
    The
    2.64
    ra
    2.64
    na
    2.56
    5
    2.48
    c
    2.42
    In
    2.39
    ro
    2.36
    Activations Density 0.002%

    No Known Activations