© 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. 34-GEMMASCOPE-RES-131K
    7. 116875
    Prev
    Next
    INDEX
    Explanations

    expect or hope

    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
     பு
    -0.89
     this
    -0.87
     пато
    -0.84
     été
    -0.78
    zato
    -0.76
     sounds
    -0.76
    вшись
    -0.76
    StateManager
    -0.75
    hezza
    -0.75
    чел
    -0.74
    POSITIVE LOGITS
    unwrap
    2.11
    expect
    1.59
     expect
    1.45
     expecting
    1.33
     Expect
    1.32
     expectation
    1.30
     expects
    1.30
     hope
    1.28
     espero
    1.24
    Expect
    1.22
    Activations Density 0.007%

    No Known Activations