© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9236
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to the genitive/possessive suffix marker “’s.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    1.00
    ا
    0.98
    w
    0.98
    m
    0.96
    h
    0.90
    x
    0.88
    hout
    0.87
    u
    0.87
     Highness
    0.86
    en
    0.85
    POSITIVE LOGITS
     అత్య
    0.84
     prerogative
    0.82
     utilização
    0.80
    cheidung
    0.79
    ponsored
    0.77
    ustainability
    0.76
    ક્ટર
    0.76
    icherheit
    0.76
     इच्छ
    0.75
    ək
    0.75
    Activations Density 0.293%

    No Known Activations