© 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. 10-GEMMASCOPE-RES-131K
    7. 39024
    Prev
    Next
    INDEX
    Explanations

    YouTube links, TiO2, watermelon

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

    chemical formulas containing titanium dioxide (TiO2).

    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
    ｄ
    -3.06
    ization
    -2.58
     sebagai
    -2.55
    m
    -2.50
    蟊
    -2.41
    蹕
    -2.41
    IN
    -2.38
    )”
    -2.34
    :')
    -2.31
    bbling
    -2.31
    POSITIVE LOGITS
    </i>
    2.91
    2
    2.78
    -
    2.72
    5
    2.31
    '
    2.28
     -"
    2.13
    かっこ
    2.05
    6
    2.05
     -
    2.03
    在意
    2.00
    Activations Density 0.002%

    No Known Activations