© 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. 106839
    Prev
    Next
    INDEX
    Explanations

    service discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    intă
    -0.75
     وسائل
    -0.71
     пород
    -0.68
    kov
    -0.68
    Ố
    -0.67
    projectId
    -0.67
     Nobu
    -0.66
     buffs
    -0.66
    ík
    -0.66
    プロジェクト
    -0.66
    POSITIVE LOGITS
     advertise
    1.08
     service
    1.08
     discovery
    1.05
     advertisement
    1.02
    Advertisement
    0.96
     advertised
    0.96
    getService
    0.93
    discovery
    0.92
     advertising
    0.91
     getService
    0.91
    Activations Density 0.021%

    No Known Activations