© 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. 61471
    Prev
    Next
    INDEX
    Explanations

    date and time formatting

    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
    ’
    -1.55
    s
    -1.53
     \
    -1.53
    選んだ
    -1.51
    ⍺
    -1.47
     pfle
    -1.46
    cer
    -1.45
    out
    -1.40
    ol
    -1.40
    はは
    -1.37
    POSITIVE LOGITS
    嫱
    1.49
    venge
    1.44
     菇
    1.42
     geweldig
    1.42
     spørsmål
    1.41
    unuz
    1.41
    baik
    1.40
    itahu
    1.40
    页面存档备份
    1.39
    ⚣
    1.39
    Activations Density 0.004%

    No Known Activations