© 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. 10-GEMMASCOPE-RES-131K
    7. 123650
    Prev
    Next
    INDEX
    Explanations

    scripture 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_10/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
     as
    -1.91
     such
    -1.83
     like
    -1.72
     including
    -1.64
     with
    -1.60
     until
    -1.59
     this
    -1.55
     so
    -1.51
    で見る
    -1.50
     within
    -1.48
    POSITIVE LOGITS
    5
    2.67
    1
    2.27
    6
    2.19
    7
    2.16
    2
    1.91
    9
    1.87
    8
    1.84
    3
    1.78
    ↵↵
    1.68
    4
    1.68
    Activations Density 0.009%

    No Known Activations