© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14487
    Prev
    Next
    INDEX
    Explanations

    new tab/window/browser

    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_22/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
     that
    -1.92
     either
    -1.56
     Either
    -1.36
    つづく
    -1.34
     the
    -1.30
    で見る
    -1.30
    になったら
    -1.29
     Bucure
    -1.26
     Qualquer
    -1.19
    来週
    -1.18
    POSITIVE LOGITS
     människor
    1.41
    0
    1.30
    でしょうね
    1.23
    dieron
    1.22
    結構
    1.21
    6
    1.19
    3
    1.19
    標準
    1.16
    問題は
    1.13
    時間も
    1.12
    Activations Density 0.001%

    No Known Activations