© 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. 82812
    Prev
    Next
    INDEX
    Explanations

    System or arguments

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

    The neuron is specialized to spot numeric tokens or digit sequences (e.g. version numbers, dates, 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_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
     watched
    -0.74
    łej
    -0.70
     beautiful
    -0.68
     XT
    -0.67
    estly
    -0.67
     primera
    -0.65
    staticmethod
    -0.65
    きたいと思います
    -0.65
     stator
    -0.64
    フリ
    -0.64
    POSITIVE LOGITS
     przew
    0.84
     remodeling
    0.79
     franco
    0.79
    apparently
    0.76
     abuelo
    0.75
    ENSEN
    0.73
    atika
    0.73
     thoại
    0.72
     finite
    0.72
     appar
    0.71
    Activations Density 0.027%

    No Known Activations