© 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. 39539
    Prev
    Next
    INDEX
    Explanations

    nucleoside analogs and chemical prefixes

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

    prime notation (') in chemical and mathematical formulas.

    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
    焄
    -3.30
    s
    -2.70
    )’
    -2.56
    ですが
    -2.55
    瑧
    -2.45
    鳯
    -2.38
    ſelves
    -2.30
    琑
    -2.27
    诒
    -2.25
    砗
    -2.20
    POSITIVE LOGITS
    珦
    3.16
    卝
    2.80
    '-
    2.63
    橚
    2.61
     we
    2.58
    凩
    2.55
     agujero
    2.50
     Перейти
    2.48
     -'
    2.42
    1
    2.42
    Activations Density 0.007%

    No Known Activations