© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    Also followed by pronoun/article

    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
     However
    -2.23
     In
    -1.93
    in
    -1.88
     either
    -1.70
     both
    -1.66
     
    -1.65
     juiste
    -1.62
     however
    -1.58
     With
    -1.55
    me
    -1.48
    POSITIVE LOGITS
    牁
    1.46
    liess
    1.46
     ∼
    1.44
     própri
    1.44
    ♪♪
    1.42
     rumoured
    1.41
    artet
    1.41
    irte
    1.39
     kwamba
    1.39
     verhind
    1.39
    Activations Density 0.023%

    No Known Activations