© 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. 44828
    Prev
    Next
    INDEX
    Explanations

    pH values around 7

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

    mentions of pH values around 7.0-7.5, which is the neutral pH range.

    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
     are
    -2.13
     that
    -1.77
     it
    -1.70
    </th>
    -1.53
     who
    -1.50
     their
    -1.42
     sostiene
    -1.41
    xfb
    -1.39
    mathrm
    -1.39
     how
    -1.38
    POSITIVE LOGITS
     större
    1.54
    توضیحات
    1.39
     Tatsache
    1.34
     меня
    1.34
     برای
    1.34
     „
    1.34
    Rumah
    1.29
    Without
    1.26
    معرفی
    1.26
    小行星
    1.23
    Activations Density 0.027%

    No Known Activations