© 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. 34-GEMMASCOPE-RES-131K
    4. 116522
    Prev
    Next
    INDEX
    Explanations

    expressing uncertainty or 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_34/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
    usually
    -2.02
    basically
    -1.57
    almost
    -1.54
     soooo
    -1.54
    obviously
    -1.50
    often
    -1.48
     Dinas
    -1.47
     praticamente
    -1.47
    mostly
    -1.45
    typically
    -1.45
    POSITIVE LOGITS
     or
    3.00
    ?
    2.88
     perhaps
    2.58
     since
    2.47
     maybe
    2.31
     Perhaps
    2.27
     Maybe
    2.23
     although
    2.13
    ?)
    1.99
     possibly
    1.90
    Activations Density 0.137%

    No Known Activations