© 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. 22-GEMMASCOPE-RES-131K
    7. 15538
    Prev
    Next
    INDEX
    Explanations

    template

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

    The neuron activates on occurrences of the word “template” (in any case or abbreviation like “TEMPLATE,” “tmpl,” etc.) in code comments, filenames, or text.

    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
    s
    -2.70
     \&
    -2.50
     \_
    -2.36
     \{
    -2.36
    大半
    -2.34
    全都
    -2.33
     dejected
    -2.23
    }
    -2.20
    \_
    -2.20
     They
    -2.17
    POSITIVE LOGITS
    퐹
    2.59
    i
    2.34
    Ⲉ
    2.31
    昻
    2.27
    鐒
    2.23
    ちゃんは
    2.17
    ਃ
    2.16
    接下來
    2.09
    ホルダー
    2.08
    Make
    2.06
    Activations Density 0.023%

    No Known Activations