© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39133
    Prev
    Next
    INDEX
    Explanations

    possessives and plurals

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

    The neuron strongly responds to the typographic apostrophe character (as used in contractions and possessives).

    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
    之色
    -1.15
    的气息
    -1.03
     fotografie
    -1.02
    🧾
    -1.02
     oku
    -1.02
    🏭
    -1.01
     geda
    -1.00
     ammi
    -0.99
    ––––
    -0.98
     inició
    -0.98
    POSITIVE LOGITS
     your
    1.97
     it
    1.59
     you
    1.54
     there
    1.30
     escalera
    1.21
    有不少
    1.18
    It
    1.13
     byste
    1.12
    .”
    1.11
    してた
    1.11
    Activations Density 0.022%

    No Known Activations