© 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. 10-GEMMASCOPE-RES-131K
    7. 71268
    Prev
    Next
    INDEX
    Explanations

    javascript types

    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
     altamente
    -1.91
     elegante
    -1.66
     amazingly
    -1.65
     zwanzig
    -1.60
     cheia
    -1.60
     mostrando
    -1.59
    recently
    -1.58
    chsel
    -1.52
    often
    -1.51
     famoso
    -1.51
    POSITIVE LOGITS
     would
    2.20
    0
    2.14
     could
    2.09
     with
    2.05
     However
    2.03
    This
    1.93
     Regardless
    1.89
     this
    1.88
     Those
    1.87
    Every
    1.84
    Activations Density 0.006%

    No Known Activations