© 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. 34-GEMMASCOPE-RES-131K
    7. 108310
    Prev
    Next
    INDEX
    Explanations

    introduction to technical texts

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

    The neuron fires on standalone numeric tokens and path‐style separators (digits or “/”) commonly found in things like patent numbers or import paths.

    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
     traduce
    -0.87
    microbial
    -0.83
     atenta
    -0.79
    roughts
    -0.79
     gramas
    -0.75
    eapon
    -0.75
    打工
    -0.75
    miesz
    -0.74
     ぼ
    -0.73
    եղ
    -0.71
    POSITIVE LOGITS
     column
    1.03
    ბ
    0.84
     magnetization
    0.83
     boil
    0.82
     IEC
    0.81
    arag
    0.78
     Mets
    0.77
     chloro
    0.77
    ukt
    0.76
     presump
    0.76
    Activations Density 0.000%

    No Known Activations