© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54248
    Prev
    Next
    INDEX
    Explanations

    bible chapter and verse references

    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
     in
    -1.34
     without
    -1.26
     took
    -1.13
     during
    -1.02
     one
    -1.02
     as
    -1.01
     should
    -1.01
     with
    -1.01
     despite
    -1.00
     at
    -0.98
    POSITIVE LOGITS
     และ
    1.72
    และ
    1.61
     And
    1.30
    brtc
    1.22
     แต่
    1.09
    そして
    1.05
    至于
    1.05
    llac
    1.04
     및
    1.03
    baly
    1.02
    Activations Density 0.013%

    No Known Activations