© 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. 75248
    Prev
    Next
    INDEX
    Explanations

    partners in projects

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

    The neuron specializes in spotting structured numeric and alphanumeric identifiers—dates, project codes, section or partner numbers, and similar document‐labeling sequences.

    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
    OOTDTY
    -1.43
    🖇
    -1.37
    日時
    -1.36
    出来ました
    -1.36
    当我
    -1.35
    There
    -1.35
    كانت
    -1.34
    Limpiar
    -1.33
    資料來源
    -1.33
    Before
    -1.33
    POSITIVE LOGITS
     it
    1.93
     to
    1.40
     such
    1.37
    尤其
    1.20
    向了
    1.19
    笙
    1.19
    ﴾
    1.16
     für
    1.16
    sibilità
    1.16
     you
    1.15
    Activations Density 0.122%

    No Known Activations