© 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. 10-GEMMASCOPE-RES-131K
    4. 130764
    Prev
    Next
    INDEX
    Explanations

    price, dollar amounts, skill levels

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

    The neuron fires on formatting and metadata tokens—e.g. markup delimiters (HTML/XML tags), diff-header line numbers, and other structural punctuation.

    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
    </em>
    -1.45
    </h3>
    -1.38
    ].
    -1.36
     else
    -1.30
    </blockquote>
    -1.30
    asyonu
    -1.23
    </h2>
    -1.21
     do
    -1.20
     i
    -1.20
    </i>
    -1.20
    POSITIVE LOGITS
     domés
    1.56
     они
    1.55
    ędzynarod
    1.52
     domingos
    1.51
     теперь
    1.49
     mulai
    1.49
     pertama
    1.49
    autogui
    1.48
     если
    1.46
     urbanas
    1.46
    Activations Density 0.001%

    No Known Activations