© 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. 108448
    Prev
    Next
    INDEX
    Explanations

    Boko Haram, NPP govt, Nigerians, apologise

    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
    抬起
    -1.03
    颚
    -0.94
    白色的
    -0.90
     a
    -0.88
     Российской
    -0.88
    ¹)
    -0.87
    */)
    -0.87
    なんだか
    -0.86
    )()
    -0.85
     Redewendung
    -0.85
    POSITIVE LOGITS
     govt
    1.59
     gov
    1.36
     Govt
    1.26
     clarifies
    1.05
    每個
    1.02
    侈
    0.98
    ussure
    0.97
    只需
    0.97
    viamo
    0.93
    Govt
    0.92
    Activations Density 0.008%

    No Known Activations