© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127269
    Prev
    Next
    INDEX
    Explanations

    external links

    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
     the
    -2.16
     your
    -1.94
     all
    -1.86
     both
    -1.82
    ~ 
    -1.69
    ၜ
    -1.66
     and
    -1.63
     an
    -1.60
    غيرة
    -1.60
     several
    -1.59
    POSITIVE LOGITS
    \
    1.98
     podría
    1.75
     ravaged
    1.74
     nieuwe
    1.70
     incred
    1.70
    还是要
    1.65
     jego
    1.64
    0
    1.63
     российских
    1.58
    ↵↵
    1.56
    Activations Density 0.004%

    No Known Activations