© 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. 119402
    Prev
    Next
    INDEX
    Explanations

    `source` followed by `=`

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

    URL parameters, specifically the underscore character in "utm_source" and "utm_medium" tracking parameters.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    It
    -1.52
    ウェル
    -1.42
     какое
    -1.38
    ねー
    -1.36
    When
    -1.36
    Things
    -1.34
    jarati
    -1.34
    日を
    -1.33
     celebrid
    -1.31
    شویی
    -1.30
    POSITIVE LOGITS
     parete
    1.52
     giacca
    1.48
    𓆜
    1.47
    <td>
    1.42
    Otras
    1.41
     particular
    1.38
     scattata
    1.34
    ↵↵
    1.34
    ='_
    1.33
     chiusura
    1.32
    Activations Density 0.002%

    No Known Activations