Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8687
    Prev
    Next
    INDEX
    Explanations

    chemical bonds

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

    chemical bonds and elements in scientific notation (particularly C-H, C-N, and metal elements).

    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
     water
    -0.79
     Flüssigkeit
    -0.76
     ice
    -0.75
     heck
    -0.74
     mengam
    -0.73
     parcial
    -0.72
     allow
    -0.71
    setDisabled
    -0.71
     what
    -0.70
    сыпа
    -0.70
    POSITIVE LOGITS
     atoms
    0.94
    ≡
    0.82
     Atom
    0.82
     atom
    0.82
    躪
    0.80
     spart
    0.80
     sover
    0.79
     inox
    0.78
    Ỏ
    0.78
     tenta
    0.78
    Activations Density 0.064%

    No Known Activations