© 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. 49087
    Prev
    Next
    INDEX
    Explanations

    hostnames and IP addresses or names

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

    The neuron fires on numeric tokens that make up the loopback IPv4 address (127.0.0.1).

    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
    verticalLayout
    -0.73
    erals
    -0.71
    orios
    -0.71
    rels
    -0.71
    loss
    -0.71
    haft
    -0.70
    颌
    -0.70
     birds
    -0.69
     and
    -0.69
    二人
    -0.69
    POSITIVE LOGITS
     Luch
    0.79
    IFFS
    0.76
    inephrine
    0.75
     Hosts
    0.74
     Muy
    0.74
     multe
    0.72
    Hos
    0.72
    folgen
    0.72
    客房
    0.71
     őket
    0.71
    Activations Density 0.006%

    No Known Activations