© 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. 84128
    Prev
    Next
    INDEX
    Explanations

    Good beer

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

    The neuron activates on standalone numeric literals in code snippets.

    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
    pado
    -1.02
    Except
    -0.96
     except
    -0.90
     kanskje
    -0.89
     Except
    -0.87
    ですかね
    -0.87
    except
    -0.86
    かで
    -0.82
     akar
    -0.82
    anyar
    -0.81
    POSITIVE LOGITS
    مبر
    0.84
     medically
    0.76
     RCS
    0.75
    ciale
    0.74
    内容
    0.74
     Kompon
    0.73
    след
    0.72
     российских
    0.71
    月号
    0.71
    Mux
    0.71
    Activations Density 0.003%

    No Known Activations