© 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. 104281
    Prev
    Next
    INDEX
    Explanations

    lower value or score

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

    The neuron is specialized to detect numeric values and quantitative expressions (e.g. numbers, units, or measurements) 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_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
     even
    -1.18
     with
    -1.05
     allerede
    -1.02
     without
    -0.97
     berkaitan
    -0.96
     fortfarande
    -0.94
     сделать
    -0.92
     Mockito
    -0.92
     include
    -0.92
     will
    -0.92
    POSITIVE LOGITS
    ఁ
    1.02
     Unii
    0.98
     Fabrication
    0.97
     값
    0.97
     lesquelles
    0.96
    licante
    0.94
     idéal
    0.94
    बर
    0.94
     Росії
    0.94
     Wij
    0.93
    Activations Density 0.018%

    No Known Activations