© 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. 22-GEMMASCOPE-RES-131K
    7. 68749
    Prev
    Next
    INDEX
    Explanations

    legal, sports, or technical terms

    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
    inWeight
    -1.26
     sorriso
    -1.24
     implor
    -1.20
     fervent
    -1.17
     shimmering
    -1.16
     grumpy
    -1.15
     mangled
    -1.15
     玄関
    -1.15
     despicable
    -1.14
     dilapidated
    -1.12
    POSITIVE LOGITS
     because
    1.84
     but
    1.64
     that
    1.52
     this
    1.38
     these
    1.34
     when
    1.32
     important
    1.30
     it
    1.28
     only
    1.28
     which
    1.27
    Activations Density 0.083%

    No Known Activations