© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34841
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

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

    The neuron activates on numeric literals (i.e. numbers or digits) 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
    ImmutableList
    -1.03
    كويكب
    -1.00
     från
    -0.97
    glDelete
    -0.96
     suffix
    -0.96
     высокие
    -0.96
    smallest
    -0.94
    цио
    -0.93
    zzjoni
    -0.93
     Auswahl
    -0.93
    POSITIVE LOGITS
     américa
    1.00
    优秀
    0.94
    亮点
    0.85
    こない
    0.83
     inquired
    0.83
     vreme
    0.82
    Situ
    0.81
    强度
    0.80
    这类
    0.80
     northwestern
    0.80
    Activations Density 0.012%

    No Known Activations