© 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. 10-GEMMASCOPE-RES-131K
    7. 101317
    Prev
    Next
    INDEX
    Explanations

    chemical bond

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

    chemical bonds in scientific text.

    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
    脔
    -2.02
     autorisation
    -1.91
     balles
    -1.88
     perles
    -1.83
    จาก
    -1.81
     ruines
    -1.77
     causer
    -1.70
    聍
    -1.68
    阄
    -1.66
     vertes
    -1.65
    POSITIVE LOGITS
     that
    2.09
    '
    1.86
     cuida
    1.80
     citada
    1.79
     youngsters
    1.76
     escuchadas
    1.67
     promete
    1.67
    妘
    1.66
     citar
    1.65
     AND
    1.63
    Activations Density 0.039%

    No Known Activations