© 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. 119117
    Prev
    Next
    INDEX
    Explanations

    metal ions with charges

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

    chemical elements and metal ions, particularly when represented with charge notations like Fe2+ or Mg2+.

    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
    identes
    -0.81
     onStop
    -0.77
     freedom
    -0.71
    biega
    -0.70
     FileWriter
    -0.68
    关联
    -0.68
     kê
    -0.67
    Vegeu
    -0.67
    antino
    -0.65
     negativo
    -0.65
    POSITIVE LOGITS
     ions
    2.91
     cations
    2.27
     ion
    2.13
    ions
    1.76
     Ion
    1.73
    Ion
    1.63
     cation
    1.48
     ionic
    1.45
     metal
    1.33
    离子
    1.32
    Activations Density 0.173%

    No Known Activations