© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129590
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and chemistry terms

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

    pairs of characters or symbols in parentheses or code-like notation, especially when they appear in mathematical or programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    opal
    -0.96
     qPCR
    -0.91
     spune
    -0.82
     âgées
    -0.79
    うわ
    -0.79
    ようになります
    -0.79
    ๕
    -0.79
     ControllerBase
    -0.79
     its
    -0.78
    ке
    -0.78
    POSITIVE LOGITS
     ogen
    0.94
     friendships
    0.85
    IGNS
    0.85
    距離
    0.84
     꽃
    0.84
     bardak
    0.83
    olarmente
    0.83
    діо
    0.83
    ationen
    0.82
    bindung
    0.82
    Activations Density 0.014%

    No Known Activations