© 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. 22-GEMMASCOPE-RES-131K
    7. 129121
    Prev
    Next
    INDEX
    Explanations

    the end of sentences

    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
    compared
    -1.01
     срав
    -1.01
    unfortunately
    -0.98
     ridiculously
    -0.96
     vergleich
    -0.96
     ridiculous
    -0.95
     filosof
    -0.93
     traduc
    -0.91
     Vergleich
    -0.91
     compared
    -0.90
    POSITIVE LOGITS
     this
    1.26
     moreover
    1.17
     therefore
    1.16
     furthermore
    1.12
     Furthermore
    1.12
    Furthermore
    1.05
     either
    1.04
     so
    1.04
     Moreover
    1.03
     consequently
    1.03
    Activations Density 0.059%

    No Known Activations