© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78707
    Prev
    Next
    INDEX
    Explanations

    ions and ionization

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

    terms related to ions, electricity, ozone, and other scientific measurements in air purification and plasma technology.

    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
     darkening
    -0.79
     dunklen
    -0.77
     Lilly
    -0.75
    //=
    -0.71
     Frühl
    -0.71
     cosmos
    -0.70
    իկ
    -0.70
     dunk
    -0.70
    jubljana
    -0.69
     }^{*
    -0.68
    POSITIVE LOGITS
     ion
    1.83
     ions
    1.79
     Ion
    1.64
    Ion
    1.47
     ionization
    1.44
     ionized
    1.29
     negative
    1.19
     anion
    1.12
     ION
    1.12
    ionization
    1.11
    Activations Density 0.029%

    No Known Activations