© 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. 67325
    Prev
    Next
    INDEX
    Explanations

    modal verbs and possibility

    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
    sometimes
    -1.45
     parfois
    -1.35
    often
    -1.33
     وصلة
    -1.23
     prêtre
    -1.23
     vostre
    -1.22
     automobili
    -1.17
     souvent
    -1.17
     Skyscanner
    -1.17
     sirena
    -1.13
    POSITIVE LOGITS
     will
    2.31
     if
    2.31
     would
    1.95
     might
    1.91
     possibly
    1.85
     likely
    1.84
     may
    1.79
     could
    1.77
     but
    1.76
     possible
    1.52
    Activations Density 0.032%

    No Known Activations