© 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. 59450
    Prev
    Next
    INDEX
    Explanations

    chemical bonds

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

    technical or scientific content with numbers, specialized terminology, and symbols.

    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
    mtime
    -0.84
     prestasi
    -0.76
     dönt
    -0.75
    committees
    -0.73
    DOUT
    -0.72
    ClientRect
    -0.71
    ⌕
    -0.71
     Final
    -0.70
     Theres
    -0.70
    cosp
    -0.69
    POSITIVE LOGITS
     bond
    1.25
    bond
    1.05
     bonds
    1.01
     hydrogen
    0.99
     Bond
    0.94
     замести
    0.93
    Hydrogen
    0.93
     Hydrogen
    0.92
    جز
    0.89
    Bond
    0.87
    Activations Density 0.013%

    No Known Activations