© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43046
    Prev
    Next
    INDEX
    Explanations

    script interpreter paths starting with /usr/

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     constituye
    -1.98
    訁
    -1.91
     outras
    -1.90
     constituyen
    -1.89
     vervolgens
    -1.88
     amables
    -1.88
    ありますが
    -1.87
     servido
    -1.86
    嗱
    -1.83
     bazı
    -1.82
    POSITIVE LOGITS
    ,”
    1.87
    .
    1.84
    </i>
    1.83
    </th>
    1.82
    When
    1.78
    :
    1.77
     "..\..\..\
    1.77
     немного
    1.76
    they
    1.72
    !
    1.72
    Activations Density 0.006%

    No Known Activations