© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75083
    Prev
    Next
    INDEX
    Explanations

    contingent on conditions

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

    This neuron detects mentions of quantitative metrics or numeric measurements (e.g. revenue, profits, percentages, years, account counts).

    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
    )_{
    -0.90
    ținut
    -0.88
     остается
    -0.88
    羌
    -0.88
    bmod
    -0.84
     portrayed
    -0.84
    Nio
    -0.84
     at
    -0.84
     opět
    -0.83
    想
    -0.83
    POSITIVE LOGITS
     when
    1.61
     because
    1.44
     due
    1.34
     بسبب
    1.20
     following
    1.13
     related
    1.10
    เพราะ
    1.05
     etc
    1.02
    专门
    1.02
     এই
    0.99
    Activations Density 0.079%

    No Known Activations