© 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. 9153
    Prev
    Next
    INDEX
    Explanations

    news and media

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

    The neuron activates on standalone headlines or section‐heading lines—short, title-style text segments that introduce an article or section.

    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
    pantalon
    -1.56
     Дата
    -1.44
    Pendidikan
    -1.40
     ehemalige
    -1.39
    これも
    -1.38
    modèle
    -1.38
     Cbd
    -1.38
    selbe
    -1.37
    当然
    -1.36
     nurturing
    -1.34
    POSITIVE LOGITS
    薷
    2.20
     and
    1.63
    🧍
    1.61
    😯
    1.59
    ❣
    1.59
    s
    1.59
    ︕
    1.59
    獁
    1.53
    .”
    1.51
     レトロ
    1.51
    Activations Density 0.013%

    No Known Activations