© 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. 22-GEMMASCOPE-RES-131K
    7. 33949
    Prev
    Next
    INDEX
    Explanations

    change, diff, and delta

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

    The neuron activates on terms that denote modifications or updates (e.g. changed, changes, diff, update, modified).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    涯
    -0.96
     skóry
    -0.95
     сына
    -0.92
     plomo
    -0.91
    ALLAS
    -0.91
     beteken
    -0.90
    Reached
    -0.90
     cukru
    -0.90
    rainy
    -0.90
    ⏬
    -0.88
    POSITIVE LOGITS
     changes
    1.38
     change
    1.24
     chitarra
    1.22
     Perubahan
    1.22
     нови
    1.13
     Changes
    1.09
    changes
    1.08
     between
    1.07
     между
    1.02
    vedades
    0.98
    Activations Density 0.062%

    No Known Activations