© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55805
    Prev
    Next
    INDEX
    Explanations

    change to a value

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

    The neuron fires on language describing quantitative changes or fluctuations—e.g. verbs and terms that report increases, drops, boosts, or other shifts in numerical measures.

    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
     capucha
    -1.60
     almohada
    -1.49
     kérd
    -1.48
     mascarilla
    -1.39
     ganchillo
    -1.36
     jellemző
    -1.34
     lehetős
    -1.34
     manualidades
    -1.34
     gorro
    -1.33
     rayas
    -1.31
    POSITIVE LOGITS
     to
    8.38
    到
    2.55
     إلى
    2.45
    至
    2.05
    to
    2.05
     đến
    1.85
    到了
    1.56
     至
    1.46
    ถึง
    1.42
     到
    1.41
    Activations Density 0.136%

    No Known Activations