© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1645
    Prev
    Next
    INDEX
    Explanations

    Neon Therapeutics

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

    indentation and spacing patterns in formatted text documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily activates on numeric tokens, especially decimal or floating-point numbers.

    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
    rainian
    -1.60
     jezt
    -1.54
     nachher
    -1.48
    蓠
    -1.45
     onsdag
    -1.45
     dépasser
    -1.45
     quaisquer
    -1.43
     municípios
    -1.43
     использовании
    -1.43
    XmlRootElement
    -1.43
    POSITIVE LOGITS
     was
    1.30
    </strong>
    1.27
    </h2>
    1.27
     so
    1.25
    よろしくお願いします
    1.20
     komme
    1.16
     what
    1.15
    0
    1.13
    </h3>
    1.12
     manchmal
    1.12
    Activations Density 0.000%

    No Known Activations