© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23771
    Prev
    Next
    INDEX
    Explanations

    atomic orbitals and electronic states

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

    scientific notation and mathematical symbols in physics or chemistry papers.

    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
     bordeaux
    -0.78
     Eta
    -0.77
     можешь
    -0.73
    ริง
    -0.73
     Thiết
    -0.72
     essences
    -0.71
    ühle
    -0.70
    lehem
    -0.69
     keys
    -0.68
    Pha
    -0.68
    POSITIVE LOGITS
     NS
    0.86
     d
    0.85
     ns
    0.82
    Ḵ
    0.79
     lone
    0.78
     valence
    0.77
     px
    0.77
     p
    0.75
     s
    0.74
     outer
    0.74
    Activations Density 0.032%

    No Known Activations