© 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. 108093
    Prev
    Next
    INDEX
    Explanations

    Ministry of

    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
    mgr
    -1.09
     Geschenk
    -0.93
    と思う
    -0.93
     mittelalter
    -0.91
     beherr
    -0.90
    に
    -0.88
     geschlossen
    -0.86
     unangemess
    -0.86
     Schlafzimmer
    -0.85
    一部分
    -0.85
    POSITIVE LOGITS
     of
    1.20
     Itália
    1.12
     Espanha
    0.98
     health
    0.94
     responsible
    0.92
     Health
    0.91
    Minist
    0.91
     liever
    0.89
     Ministère
    0.87
     Ministry
    0.84
    Activations Density 0.007%

    No Known Activations