© 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. 73654
    Prev
    Next
    INDEX
    Explanations

    Creek Emulator .org

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

    The neuron fires strongly on named technical entities and metadata—project/library names, version numbers, and other proper‐noun identifiers.

    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
    gnome
    -0.78
     bear
    -0.77
    门店
    -0.74
    glLoad
    -0.72
    enos
    -0.72
    شارة
    -0.70
    entrums
    -0.70
    izados
    -0.69
     Ρ
    -0.69
    pegno
    -0.69
    POSITIVE LOGITS
    hahahaha
    0.86
     whereby
    0.83
     geçi
    0.78
     ledit
    0.75
     Tarantino
    0.74
     contemp
    0.73
    驶
    0.73
    Batteries
    0.72
     lequel
    0.71
    ukunft
    0.71
    Activations Density 0.169%

    No Known Activations