© 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. 41494
    Prev
    Next
    INDEX
    Explanations

    LaTeX drawing commands

    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
    er
    -1.66
    🌸
    -1.48
    饮食
    -1.48
    ers
    -1.41
    </u>
    -1.38
    le
    -1.36
    </h5>
    -1.35
    </h4>
    -1.34
     esimer
    -1.33
    💖
    -1.33
    POSITIVE LOGITS
    巨大的
    1.46
    bukkit
    1.45
    ſelves
    1.41
    ayant
    1.38
    OTHER
    1.36
    parsedMessage
    1.36
     extremely
    1.35
    都不是
    1.34
    的人都
    1.34
     چقدر
    1.32
    Activations Density 0.003%

    No Known Activations