© 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. 58555
    Prev
    Next
    INDEX
    Explanations

    roman numeral oxidation states

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

    chemical elements in their oxidation states, particularly notated with Roman numerals in parentheses.

    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
     beyond
    -0.90
     past
    -0.85
     overlook
    -0.76
    beforeAll
    -0.75
     złoż
    -0.74
     Registration
    -0.72
     along
    -0.72
    lipse
    -0.71
    ETHYL
    -0.68
    ombus
    -0.68
    POSITIVE LOGITS
     oxidation
    1.73
     Oxidation
    1.27
    oxidation
    1.16
     valence
    1.14
     state
    1.01
    state
    1.00
     formal
    0.93
     estado
    0.89
    状态
    0.88
     états
    0.88
    Activations Density 0.050%

    No Known Activations