© 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. 22-GEMMASCOPE-RES-131K
    7. 27428
    Prev
    Next
    INDEX
    Explanations

    consequence or conclusion

    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_22/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
     sprawie
    -0.83
     femininos
    -0.82
    lihat
    -0.82
    ！！！”
    -0.81
     Matériau
    -0.81
     from
    -0.80
     although
    -0.80
     prevents
    -0.78
     Verbesserung
    -0.78
     BioLib
    -0.77
    POSITIVE LOGITS
     поэтому
    1.82
     so
    1.78
    所以
    1.56
     therefore
    1.56
     nên
    1.43
     لذا
    1.41
     所以
    1.38
     Поэтому
    1.33
     perciò
    1.33
     hence
    1.30
    Activations Density 0.050%

    No Known Activations