© 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. 28011
    Prev
    Next
    INDEX
    Explanations

    introductory phrases to discuss topics

    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
     encantó
    -0.94
     frå
    -0.94
     vü
    -0.91
    long
    -0.90
     cascada
    -0.90
     skjø
    -0.90
    vari
    -0.88
    cons
    -0.88
     Technische
    -0.88
     sitesinde
    -0.88
    POSITIVE LOGITS
     here
    1.81
     herein
    1.13
    wegian
    1.09
     herewith
    1.07
     now
    1.07
    륜
    1.05
     relógio
    1.05
     briefly
    1.04
     hereby
    1.02
     bebê
    1.02
    Activations Density 0.092%

    No Known Activations