© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15063
    Prev
    Next
    INDEX
    Explanations

    start of a possessive or contraction

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

    The neuron fires on the apostrophe character (particularly the curly ’ used in contractions like “That’s”).

    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
     These
    -2.67
    >>>>>>
    -2.56
    酲
    -2.42
     icona
    -2.41
    鈇
    -2.34
     batteria
    -2.27
    stration
    -2.27
    ⁉
    -2.20
    鶲
    -2.20
    ???:
    -2.19
    POSITIVE LOGITS
    '
    2.91
    /
    2.50
    :
    2.44
     \
    2.25
    ]
    2.19
     cherish
    2.19
    _
    2.16
    –
    2.11
    \
    2.08
     {
    2.03
    Activations Density 0.024%

    No Known Activations