© 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. 28404
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     Fazit
    -1.23
     its
    -1.16
     tomaron
    -1.16
     mały
    -1.13
    lerinde
    -1.12
     cittadino
    -1.06
     szczeg
    -1.04
     stratég
    -1.04
    Iš
    -1.03
    意料
    -1.03
    POSITIVE LOGITS
     still
    1.32
    VALUE
    1.01
    fié
    0.98
    uyasha
    0.97
     jeszcze
    0.95
    还是
    0.92
    Palmarès
    0.92
    техни
    0.92
     ještě
    0.91
     you
    0.91
    Activations Density 0.003%

    No Known Activations