© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15975
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron is looking for the opening delimiters of embedded server‐side code (e.g. “<?” or “<?php”).

    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
    んでも
    -1.13
    了一遍
    -1.09
    不断的
    -1.06
    assertj
    -1.04
    Кроме
    -1.00
     invitación
    -1.00
    呟
    -0.99
    WindowConstants
    -0.98
    ribune
    -0.98
     votación
    -0.98
    POSITIVE LOGITS
    為に
    1.13
    が可能
    1.09
    uncia
    1.08
     hés
    1.06
    さあ
    1.05
    あぁ
    1.05
    webElement
    1.04
    вушка
    1.03
     mépris
    1.01
     Dí
    1.00
    Activations Density 0.005%

    No Known Activations