© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59160
    Prev
    Next
    INDEX
    Explanations

    counting and mathematical operations

    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
     has
    -1.49
     by
    -1.38
     all
    -1.32
     first
    -1.30
     even
    -1.27
     without
    -1.27
     Desember
    -1.26
     one
    -1.23
    Even
    -1.23
    All
    -1.22
    POSITIVE LOGITS
     vôtre
    1.48
     nôtre
    1.39
     méda
    1.38
     cinquième
    1.35
     conducteur
    1.35
     échange
    1.31
     広場
    1.30
     récomp
    1.29
     trône
    1.27
     dépens
    1.26
    Activations Density 0.029%

    No Known Activations