© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58316
    Prev
    Next
    INDEX
    Explanations

    legal citations and document 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
     during
    -2.06
     using
    -2.05
     after
    -1.98
     before
    -1.91
     categorized
    -1.88
     expertly
    -1.86
     having
    -1.86
     choosing
    -1.84
     battling
    -1.84
     three
    -1.84
    POSITIVE LOGITS
    9
    2.58
    7
    2.38
    8
    2.17
     zarówno
    2.13
    4
    2.05
    3
    2.02
    5
    2.02
    6
    1.92
    WAYS
    1.90
     señala
    1.90
    Activations Density 0.073%

    No Known Activations