© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63134
    Prev
    Next
    INDEX
    Explanations

    code buffers and memory

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

    The neuron is strongly activated by numeric digits (0–9) 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_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
    rigated
    -0.78
    roppo
    -0.75
    Abo
    -0.74
    hånd
    -0.72
     معد
    -0.69
    brad
    -0.68
    ेर
    -0.68
    やら
    -0.68
     abdominal
    -0.66
    nity
    -0.66
    POSITIVE LOGITS
     buffer
    1.23
    buffer
    1.00
     buffers
    0.98
    buf
    0.94
     StringIO
    0.93
    buff
    0.85
    String
    0.84
    buffers
    0.83
     Buffer
    0.82
    DataProvider
    0.81
    Activations Density 0.036%

    No Known Activations