© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130952
    Prev
    Next
    INDEX
    Explanations

    titanium dioxide and TNF

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

    chemical formulas and scientific notations, particularly TiO2 and TNF.

    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_10/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
    孓
    -2.86
    ſelves
    -2.81
    )’
    -2.41
    窠
    -2.36
    本章
    -2.30
    s
    -2.27
    哢
    -2.27
    荜
    -2.25
    ?’
    -2.23
    ственность
    -2.23
    POSITIVE LOGITS
    the
    3.06
    ing
    2.91
     รวม
    2.77
    其妙
    2.75
     '
    2.69
    some
    2.67
    ي
    2.56
    쨩
    2.53
     vastly
    2.47
     astonishing
    2.44
    Activations Density 0.014%

    No Known Activations