© 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. 75353
    Prev
    Next
    INDEX
    Explanations

    physiology, lung diseases

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

    base64/encoded characters and cryptographic data.

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

    The neuron fires on long, block‐style sequences of uppercase letters, digits, and symbols typical of Base64‐encoded or cryptographic key material.

    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
    みんなで
    -1.67
     they
    -1.65
     适合
    -1.62
     deluxe
    -1.58
    ang
    -1.55
     its
    -1.54
    咵
    -1.53
    חו
    -1.50
    繋が
    -1.41
     unseren
    -1.41
    POSITIVE LOGITS
    ícias
    1.54
    tons
    1.54
    unno
    1.52
    ſtance
    1.43
     prédio
    1.40
     berangkat
    1.40
    perity
    1.39
     fueran
    1.38
    lardan
    1.36
    ÍTICA
    1.36
    Activations Density 0.002%

    No Known Activations