© 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. 34-GEMMASCOPE-RES-131K
    7. 81446
    Prev
    Next
    INDEX
    Explanations

    possessive 's

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

    The neuron fires on the typographic right‐single‐quote/apostrophe character (’), i.e. occurrences of the curly apostrophe in possessives or contractions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    を
    -1.46
     get
    -1.32
    They
    -1.23
     お
    -1.23
    その
    -1.23
     It
    -1.23
    "
    -1.22
    примеча
    -1.20
    などなど
    -1.19
     Some
    -1.18
    POSITIVE LOGITS
    s
    2.17
    ⃣
    1.63
    場所で
    1.52
     hlavy
    1.52
    ️⃣
    1.49
     nadru
    1.47
     sær
    1.46
     and
    1.45
    ⛦
    1.45
     barbati
    1.43
    Activations Density 0.026%

    No Known Activations