© 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. 34-GEMMASCOPE-RES-131K
    7. 59372
    Prev
    Next
    INDEX
    Explanations

    oxygen and hydroxide (OH)

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

    chemical formulas and molecular structures 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_34/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
     produisent
    -0.90
    ые
    -0.80
     lilla
    -0.80
    loyment
    -0.79
    鼾
    -0.79
     parlent
    -0.78
     suivent
    -0.77
    yoruz
    -0.75
     WE
    -0.75
    bürgermeister
    -0.75
    POSITIVE LOGITS
    uparrow
    0.93
    DH
    0.87
     ↓
    0.82
    скаго
    0.81
     qualche
    0.76
    ڌ
    0.76
    rét
    0.75
     ısı
    0.75
     RELE
    0.75
     byproduct
    0.74
    Activations Density 0.008%

    No Known Activations