© 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. 36439
    Prev
    Next
    INDEX
    Explanations

    list item 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_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
     also
    -1.90
     and
    -1.70
     этого
    -1.57
     також
    -1.57
     también
    -1.49
     также
    -1.48
     what
    -1.33
     myös
    -1.32
     this
    -1.23
     этом
    -1.20
    POSITIVE LOGITS
    <strong>
    1.52
     whereas
    1.46
     The
    1.42
     you
    1.41
    が無い
    1.34
     it
    1.30
    <b>
    1.30
    Whereas
    1.27
     they
    1.27
    薷
    1.24
    Activations Density 0.016%

    No Known Activations