© 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. 66220
    Prev
    Next
    INDEX
    Explanations

    software libraries and technical documentation

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

    The neuron is triggered by HTML/XML structural markup elements—slashes, tags (e.g. html), declarations (e.g. DTD), and related tokens like charset.

    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
    она
    -0.82
    backends
    -0.81
    athetic
    -0.77
    னர்
    -0.77
     zwi
    -0.77
     Go
    -0.77
    leis
    -0.75
     fond
    -0.74
    形态
    -0.74
     assign
    -0.74
    POSITIVE LOGITS
     Indon
    0.83
    Рейтинг
    0.82
     Scrip
    0.82
    uteria
    0.79
     idi
    0.79
    Colore
    0.79
     PARAM
    0.75
    
    0.75
    👴
    0.75
     alberi
    0.73
    Activations Density 0.002%

    No Known Activations