© 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. 34-GEMMASCOPE-RES-131K
    7. 81231
    Prev
    Next
    INDEX
    Explanations

    counting or distinguishing items

    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_34/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
    任何
    -1.52
     it
    -1.44
    ępo
    -1.29
     if
    -1.28
    biť
    -1.25
     has
    -1.25
    很多
    -1.20
    将其
    -1.20
     anything
    -1.17
     Many
    -1.17
    POSITIVE LOGITS
     different
    2.30
     selected
    2.25
     différents
    2.20
     verschillende
    2.13
     two
    2.13
    different
    2.06
     différentes
    1.97
     three
    1.92
     diferentes
    1.90
     różnych
    1.84
    Activations Density 0.734%

    No Known Activations