© 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. 20504
    Prev
    Next
    INDEX
    Explanations

    Emery, Emer

    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
    <bos>
    -2.84
    C
    -2.73
    ではでは
    -2.59
     premiere
    -2.48
     remainder
    -2.48
    笵
    -2.47
    藹
    -2.44
    ではまた
    -2.44
    军的
    -2.39
     pierwszy
    -2.34
    POSITIVE LOGITS
    滙
    2.34
    湉
    2.33
    大約
    2.27
    巿
    2.27
    或是
    2.22
     droite
    2.19
    t
    2.17
     Selasa
    2.17
    𝗧
    2.17
    ?”
    2.16
    Activations Density 0.008%

    No Known Activations