© 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. 98995
    Prev
    Next
    INDEX
    Explanations

    Q: questions

    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
     and
    -1.52
     heuti
    -0.99
     distintas
    -0.98
     different
    -0.97
     กรัม
    -0.96
     dueños
    -0.93
     zostanie
    -0.91
     otras
    -0.91
     each
    -0.91
     besonderer
    -0.90
    POSITIVE LOGITS
    :
    1.29
     praktik
    1.16
     seks
    1.13
     trône
    1.12
     seksi
    1.08
     plonge
    1.08
     florales
    1.06
     transparentes
    1.06
     kalori
    1.06
    aconda
    1.05
    Activations Density 0.191%

    No Known Activations