© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130738
    Prev
    Next
    INDEX
    Explanations

    the followed by system/data nouns

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

    The neuron is triggered by occurrences of the two-word sequence “to the.”

    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
     &
    -1.52
     and
    -1.50
    //
    -1.36
    muffin
    -1.27
    /**
    -1.26
     ندار
    -1.25
    /
    -1.24
     from
    -1.23
     vun
    -1.23
    IIII
    -1.22
    POSITIVE LOGITS
    为啥
    1.45
     its
    1.44
    ですし
    1.43
     expans
    1.38
     herhangi
    1.31
    呖
    1.30
    会出现
    1.29
    ICKS
    1.27
    ɝ
    1.27
     suoi
    1.27
    Activations Density 0.136%

    No Known Activations