© 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. 48669
    Prev
    Next
    INDEX
    Explanations

    communication services and applications

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

    The neuron fires on formal technical‐specification language—especially verbs and nouns that list or describe system capabilities and supported services (e.g. “support,” “include,” “services,” “performance,” “deployment,” 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_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
    ựu
    -0.97
    硬件
    -0.89
     başarı
    -0.84
    getLogin
    -0.81
    Nhà
    -0.79
     Gently
    -0.78
    hardware
    -0.77
     biodiesel
    -0.75
    oane
    -0.75
    Twee
    -0.74
    POSITIVE LOGITS
     applications
    1.55
     video
    1.50
     services
    1.34
    applications
    1.27
    Applications
    1.27
     APPLICATIONS
    1.24
     Video
    1.19
     Applications
    1.18
    Video
    1.14
     traffic
    1.13
    Activations Density 0.127%

    No Known Activations