© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129344
    Prev
    Next
    INDEX
    Explanations

    - RO

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

    This neuron detects page‐break or form‐feed characters marking new sections or pages.

    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
    tedì
    -2.28
     its
    -2.03
     acostumb
    -1.95
    饜
    -1.91
     chief
    -1.84
     he
    -1.84
     sufri
    -1.82
     deberá
    -1.80
     accustomed
    -1.77
     it
    -1.76
    POSITIVE LOGITS
    ’
    2.11
    乆
    2.06
     rajut
    1.92
     Selasa
    1.85
     Yani
    1.84
     ladri
    1.79
     didik
    1.77
    følgelig
    1.74
    ܊
    1.72
    푉
    1.70
    Activations Density 0.002%

    No Known Activations