© 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. 10-GEMMASCOPE-RES-131K
    7. 69731
    Prev
    Next
    INDEX
    Explanations

    ipv4ipv6 fragmentation socket

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

    The neuron is tuned to detect software or protocol version identifiers (e.g. “ipv4,” “IPv6,” “v3,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -1.97
    は無
    -1.70
     such
    -1.67
    縂
    -1.60
     However
    -1.59
     îna
    -1.59
    
    -1.58
    
    -1.55
    而去
    -1.53
     Ξ
    -1.53
    POSITIVE LOGITS
    ”？
    2.05
    ၞ
    1.96
    ”（
    1.75
    FormTagHelper
    1.71
    PickerController
    1.67
    Skocz
    1.67
    vimento
    1.66
     increíbles
    1.66
     बारे
    1.66
    （
    1.65
    Activations Density 0.007%

    No Known Activations