© 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. 67703
    Prev
    Next
    INDEX
    Explanations

    names of places and institutions

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

    The neuron fires strongly on standalone numeric tokens (digits, multi-digit numbers, ordinal numbers) wherever they appear 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
    struzione
    -0.87
     Volkes
    -0.86
     biografia
    -0.84
    OLOGÍA
    -0.83
     istr
    -0.82
     those
    -0.81
    ⒈
    -0.81
     palla
    -0.80
     whether
    -0.80
     Macht
    -0.80
    POSITIVE LOGITS
     gedacht
    0.93
     basteln
    0.85
     of
    0.83
    }%
    0.83
    心中
    0.81
    itivo
    0.79
    |()
    0.78
    沨
    0.78
     szép
    0.78
    ">(</
    0.77
    Activations Density 0.252%

    No Known Activations