© 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. 34-GEMMASCOPE-RES-131K
    7. 78041
    Prev
    Next
    INDEX
    Explanations

    change and fluctuate over time

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

    The neuron activates on words that denote change or variation over time (e.g., shift, expand, contract, fluctuate, vary).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     reduced
    -0.94
    ступил
    -0.94
     nếu
    -0.88
     diminished
    -0.88
     если
    -0.84
    nonumber
    -0.84
    aksi
    -0.83
    leş
    -0.82
    hawat
    -0.82
    Oder
    -0.81
    POSITIVE LOGITS
     depending
    1.87
     between
    1.80
     according
    1.59
    between
    1.32
    depending
    1.29
    Depending
    1.24
    according
    1.19
     Depending
    1.15
     Between
    1.13
     based
    1.11
    Activations Density 0.119%

    No Known Activations