© 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. 73349
    Prev
    Next
    INDEX
    Explanations

    Google Plus

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

    The neuron strongly activates on numeric tokens and long digit sequences (e.g. counts, IDs, timestamps) in URLs or metadata.

    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
    ieR
    -0.82
     hotspot
    -0.81
     continuum
    -0.79
    𝒲
    -0.77
     Compression
    -0.76
    xbc
    -0.76
    //};
    -0.75
     presenti
    -0.75
    晴
    -0.74
    irem
    -0.74
    POSITIVE LOGITS
     circles
    1.46
     Circles
    1.34
    circles
    1.27
    Circles
    1.17
     circle
    1.07
     +
    1.05
    circled
    0.96
     CIRCLE
    0.90
     Circle
    0.86
    +
    0.85
    Activations Density 0.030%

    No Known Activations