© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 933
    Prev
    Next
    INDEX
    Explanations

    possessive determiners and possessive marker

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

    The neuron is specialized to detect floating‐point numeric values (decimal numbers).

    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
     is
    0.67
    ['
    0.63
    에
    0.61
    type
    0.61
    的形式
    0.61
    та
    0.59
     -
    0.57
     Exception
    0.57
     =
    0.56
     '/'
    0.56
    POSITIVE LOGITS
     own
    1.10
     propio
    0.89
     propia
    0.84
     propias
    0.80
     propios
    0.80
     собстве
    0.79
     eigenes
    0.77
     própria
    0.76
     собственных
    0.74
     eigenen
    0.73
    Activations Density 0.931%

    No Known Activations