© 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. 39742
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
    3
    -2.11
    Ketika
    -1.98
    Karena
    -1.92
    今日の
    -1.91
    Cuando
    -1.88
    1
    -1.85
    Rumah
    -1.77
    t
    -1.74
    Después
    -1.65
    Harga
    -1.65
    POSITIVE LOGITS
    ”
    2.16
    摹
    1.70
    fillment
    1.65
    蓐
    1.64
     on
    1.64
    ',
    1.63
    幛
    1.61
    ),),
    1.60
    >
    1.58
    )--(
    1.55
    Activations Density 0.006%

    No Known Activations