© 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. 39615
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     sociedades
    -1.29
     what
    -1.29
     if
    -1.19
     categorized
    -1.17
     when
    -1.13
     because
    -1.10
     notable
    -1.09
    RIQUE
    -1.07
     prevent
    -1.06
     out
    -1.05
    POSITIVE LOGITS
     واتس
    1.17
     Ln
    1.17
     zeven
    1.13
    Autres
    1.13
     kuh
    1.04
    
    1.04
     delectable
    1.02
    铝
    1.00
     Bn
    1.00
     temb
    1.00
    Activations Density 0.025%

    No Known Activations