© 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. 31209
    Prev
    Next
    INDEX
    Explanations

    IP address or IPv6

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

    The neuron is primarily activated by numeric tokens—sequences of digits such as literal numbers, sizes, indices, or IP‐style numeric components.

    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
     }}</
    -0.77
    祭
    -0.76
     Metals
    -0.74
     contrase
    -0.73
    wurf
    -0.70
    ReferenceEquals
    -0.69
     Schur
    -0.69
    ameters
    -0.69
     metals
    -0.68
     inland
    -0.67
    POSITIVE LOGITS
     IPv
    1.74
     ipv
    1.34
    IPv
    1.27
    IPV
    1.07
    ipv
    1.06
     dotted
    0.98
     ip
    0.95
     IP
    0.91
     Ip
    0.88
    maske
    0.87
    Activations Density 0.035%

    No Known Activations