© 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. 22-GEMMASCOPE-RES-131K
    7. 40150
    Prev
    Next
    INDEX
    Explanations

    placeholders and special characters

    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
    *
    -3.27
    \
    -3.17
    _
    -2.88
     In
    -2.42
     We
    -2.41
    ra
    -2.33
    了一些
    -2.30
     dejando
    -2.27
    b
    -2.23
    ...?
    -2.22
    POSITIVE LOGITS
    銪
    2.59
    镦
    2.59
     siè
    2.47
    缯
    2.47
    鹇
    2.39
    鹉
    2.36
     mengucap
    2.31
    糨
    2.28
    ᕱ
    2.28
     ";
    2.28
    Activations Density 0.025%

    No Known Activations