© 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. 35675
    Prev
    Next
    INDEX
    Explanations

    modal verb followed by have

    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
     its
    -1.69
     itself
    -1.58
    腠
    -1.54
    𞤤
    -1.40
     которой
    -1.37
    ┙
    -1.32
    AddTagHelper
    -1.30
    -```
    -1.29
    onore
    -1.28
     blauwe
    -1.27
    POSITIVE LOGITS
     yourself
    2.11
     your
    1.44
     می‌توانید
    1.38
    '
    1.38
    Your
    1.33
    It
    1.30
    的眼神
    1.27
    ’
    1.26
     esetben
    1.26
    yourself
    1.25
    Activations Density 0.158%

    No Known Activations