© 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. 102787
    Prev
    Next
    INDEX
    Explanations

    comparing values using inequalities

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

    comparison operators and inequality symbols in mathematical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on numeric literals (especially decimal numbers) in the text.

    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
    атр
    -1.34
     ſie
    -1.26
     (~(
    -1.25
     misschien
    -1.24
    皷
    -1.23
    粄
    -1.22
     praticamente
    -1.20
     ſch
    -1.20
    ೯
    -1.19
    ᗨ
    -1.18
    POSITIVE LOGITS
     than
    1.69
     actually
    1.44
     only
    1.41
     even
    1.31
     góry
    1.24
     någon
    1.23
     people
    1.22
     його
    1.13
     it
    1.13
     its
    1.13
    Activations Density 0.044%

    No Known Activations