© 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. 59363
    Prev
    Next
    INDEX
    Explanations

    planning further actions

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

    This neuron detects expressions of future intent or expectation, such as “planning,” “expecting,” or “hoping.”

    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
    9
    -1.85
    1
    -1.77
     où
    -1.68
                            
    -1.63
    5
    -1.61
     WHERE
    -1.54
    8
    -1.53
    0
    -1.51
    4
    -1.50
    o
    -1.48
    POSITIVE LOGITS
    圖片來源
    1.78
    賒
    1.75
     considering
    1.73
    酩
    1.72
    摃
    1.71
     utilising
    1.70
     another
    1.70
     a
    1.69
    骓
    1.66
     overseeing
    1.62
    Activations Density 0.027%

    No Known Activations