© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73244
    Prev
    Next
    INDEX
    Explanations

    chemical element carbon

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

    chemical element symbols and isotope notation in scientific context.

    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_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
    _
    -1.84
     gelas
    -1.80
    ures
    -1.75
    They
    -1.74
    也有
    -1.63
    他们
    -1.63
     adil
    -1.59
    اً
    -1.59
     :
    -1.56
     Semoga
    -1.55
    POSITIVE LOGITS
    逞
    1.58
    禿
    1.48
    侵略
    1.33
    یین
    1.32
    AsStream
    1.30
     delineate
    1.30
    熾
    1.29
     síntesis
    1.28
     入り
    1.27
     sejam
    1.23
    Activations Density 0.055%

    No Known Activations