© 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. 10-GEMMASCOPE-RES-131K
    7. 84941
    Prev
    Next
    INDEX
    Explanations

    the word final

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

    The neuron activates strongly on occurrences of the token “final.”

    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
     siguiendo
    -2.31
     are
    -2.14
     Pokud
    -2.02
     які
    -1.99
     Tetapi
    -1.97
    勦
    -1.96
    geſ
    -1.96
    迨
    -1.95
     знаем
    -1.95
     яке
    -1.94
    POSITIVE LOGITS
    𐐪
    2.31
    ᕱ
    2.23
    ⸂
    2.20
     bygge
    2.13
    呖
    2.11
    建議
    2.08
    鲥
    2.05
     醤油
    2.02
    壟
    1.98
     cromado
    1.98
    Activations Density 0.016%

    No Known Activations