© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38731
    Prev
    Next
    INDEX
    Explanations

    hope and expectation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on words conveying expectation or hope (e.g. hope, hoped, expectation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     gezicht
    -1.55
    镚
    -1.51
    anyahu
    -1.51
    㩒
    -1.51
    
    -1.44
    茈
    -1.41
    襁
    -1.39
    銼
    -1.38
     Infór
    -1.38
     decaying
    -1.38
    POSITIVE LOGITS
    {
    2.25
     more
    1.67
     expectation
    1.59
    ers
    1.52
    ?
    1.51
    我们
    1.38
     of
    1.35
     possibility
    1.35
    </i>
    1.33
     
    1.33
    Activations Density 0.024%

    No Known Activations