© 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. 127185
    Prev
    Next
    INDEX
    Explanations

    Emma, positive comments, introduction

    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
     رائع
    -2.56
    緲
    -2.42
    歺
    -2.41
     PÅ
    -2.36
    leurs
    -2.36
    cadilly
    -2.22
     丁目
    -2.20
    liśmy
    -2.19
    糴
    -2.17
    聼
    -2.11
    POSITIVE LOGITS
    </b>
    2.56
    e
    2.48
     was
    2.45
    ut
    2.44
    d
    2.41
    us
    2.41
    no
    2.27
    io
    2.22
    ne
    2.20
    ana
    2.20
    Activations Density 0.000%

    No Known Activations