© 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. 87328
    Prev
    Next
    INDEX
    Explanations

    mom and dad

    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
    </strong>
    -1.56
     Mereka
    -1.56
     流れ
    -1.53
    asında
    -1.48
     Jednak
    -1.47
    muş
    -1.39
    </h4>
    -1.38
     Tetapi
    -1.38
     チャーム
    -1.38
    maktadır
    -1.37
    POSITIVE LOGITS
     =
    2.25
    the
    1.77
    ra
    1.69
    </i>
    1.66
    id
    1.47
    y
    1.43
    do
    1.39
    j
    1.38
    们的
    1.37
    ly
    1.36
    Activations Density 0.014%

    No Known Activations