© 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. 34-GEMMASCOPE-RES-131K
    7. 50149
    Prev
    Next
    INDEX
    Explanations

    the second in a sequence

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

    The neuron fires on tokens representing numeric values (i.e. it detects numerals).

    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
    another
    -1.30
     ANOTHER
    -1.22
     Thirdly
    -1.21
     TAMBÉM
    -1.05
     another
    -1.02
     第三
    -0.97
     otro
    -0.97
     چهارم
    -0.95
     Another
    -0.94
    )+
    -0.92
    POSITIVE LOGITS
     second
    1.73
     manuell
    0.93
    ressee
    0.91
    ॥
    0.88
     seconds
    0.88
     शुर
    0.88
    werks
    0.82
    乆
    0.82
     suavemente
    0.81
    richting
    0.80
    Activations Density 0.047%

    No Known Activations