© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12706
    Prev
    Next
    INDEX
    Explanations

    waiting or continuing

    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
     kyse
    -1.01
    BitmapFactory
    -0.94
     podremos
    -0.93
     filha
    -0.93
     venezol
    -0.92
     chilena
    -0.92
    UIFont
    -0.89
     ahol
    -0.89
    skie
    -0.88
    ToMany
    -0.88
    POSITIVE LOGITS
     awaiting
    1.18
     thinking
    1.08
     waiting
    1.05
     momentarily
    1.03
     while
    1.01
    Meanwhile
    0.99
     enquanto
    0.99
     आवश्यकता
    0.98
     temporarily
    0.98
     continues
    0.97
    Activations Density 0.008%

    No Known Activations