© 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. 110716
    Prev
    Next
    INDEX
    Explanations

    wondering or questioning

    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
    REAT
    -0.90
    istische
    -0.88
     Touchable
    -0.87
    ɦ
    -0.86
    atically
    -0.85
     DECISION
    -0.84
    timation
    -0.84
    下意识
    -0.82
    aries
    -0.81
     veo
    -0.80
    POSITIVE LOGITS
     wonder
    6.53
     wondering
    5.78
     wondered
    5.34
    wonder
    5.00
     wonders
    4.72
     Wonder
    4.66
    Wonder
    4.28
    Wondering
    3.59
     WONDER
    3.38
     question
    2.94
    Activations Density 0.147%

    No Known Activations