© 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. 73839
    Prev
    Next
    INDEX
    Explanations

    grandhotel, temporarily, .cn domains

    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
     at
    -1.98
     in
    -1.95
     if
    -1.54
     using
    -1.49
     trying
    -1.46
     should
    -1.41
     when
    -1.39
     only
    -1.38
     for
    -1.37
     any
    -1.37
    POSITIVE LOGITS
     magnifiques
    1.37
     innumer
    1.36
     srdce
    1.36
    ㈯
    1.31
     indepen
    1.30
     rů
    1.30
     œufs
    1.27
     crappy
    1.25
     vêtements
    1.25
    댔
    1.24
    Activations Density 0.004%

    No Known Activations