© 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. 66511
    Prev
    Next
    INDEX
    Explanations

    smallness or degree

    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
     makam
    -1.49
    
    -1.34
     demokra
    -1.27
    糁
    -1.26
     varier
    -1.23
     花纹
    -1.21
    choosing
    -1.20
     konser
    -1.19
    〬
    -1.17
     plafon
    -1.16
    POSITIVE LOGITS
     or
    1.33
     this
    1.27
     get
    1.20
     could
    1.19
     at
    1.17
     tiny
    1.16
     make
    1.14
     because
    1.13
     that
    1.13
     would
    1.13
    Activations Density 0.021%

    No Known Activations