© 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. 34-GEMMASCOPE-RES-131K
    4. 81377
    Prev
    Next
    INDEX
    Explanations

    html tags and structure

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

    The neuron is detecting runs of leading whitespace used for indentation in markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     toneladas
    -1.08
     this
    -1.08
     informar
    -1.06
    скажите
    -1.06
    ровка
    -1.04
    Ży
    -1.03
     completas
    -1.01
    んですよ
    -0.99
    cended
    -0.98
     rokov
    -0.95
    POSITIVE LOGITS
     <
    2.06
     a
    1.94
    <
    1.77
    "><
    1.70
    '><
    1.48
     hierfür
    1.43
    ><
    1.27
     $<
    1.17
    ;<
    1.16
     $<$
    1.12
    Activations Density 0.016%

    No Known Activations