© 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. 22-GEMMASCOPE-RES-131K
    7. 70536
    Prev
    Next
    INDEX
    Explanations

    contractions following apostrophes

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

    The neuron fires strongly on apostrophe characters (single‐quote marks), i.e. the ’ or ’ tokens used in contractions or 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
    лерея
    -1.06
    女優
    -1.02
    とはいえ
    -0.97
    購入
    -0.96
    商品の
    -0.95
     after
    -0.91
     schreef
    -0.89
    彼の
    -0.88
    と思われます
    -0.88
    不对
    -0.87
    POSITIVE LOGITS
    Interviewer
    1.08
    了自己
    1.08
    *+
    1.07
     mercancías
    1.07
    kontroll
    1.05
     göm
    1.03
    няют
    0.98
     Turm
    0.96
     içeris
    0.96
     kwamba
    0.96
    Activations Density 0.002%

    No Known Activations