© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33905
    Prev
    Next
    INDEX
    Explanations

    sections and headings

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

    This neuron detects document section headings or titles, marked by HTML heading tags (e.g. <h4>, <h5>) or Markdown header markers (e.g. ###).

    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
    Étape
    -0.98
    Formazione
    -0.97
     Američ
    -0.91
    ictured
    -0.90
     escuelas
    -0.88
    expédition
    -0.87
     będzie
    -0.87
    鹋
    -0.87
    ις
    -0.85
    älfte
    -0.84
    POSITIVE LOGITS
    靱
    0.94
        
    0.89
    ̴
    0.89
    ̈
    0.88
    oom
    0.87
    ⁷
    0.86
    ローラ
    0.84
    ␤
    0.84
    ”)
    0.84
     Geraadpleegd
    0.83
    Activations Density 0.000%

    No Known Activations