© 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. 55712
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    allergenic
    -0.85
    collo
    -0.82
     comprando
    -0.81
     aumentar
    -0.79
    痫
    -0.77
     zufrieden
    -0.75
    thie
    -0.75
     voegen
    -0.74
    だよね
    -0.73
     Führung
    -0.70
    POSITIVE LOGITS
    mover
    1.21
     $\
    1.15
    tilde
    1.02
    overline
    1.01
    ：@
    0.94
    :^
    0.90
    ˆ
    0.89
     ¯
    0.87
    lise
    0.83
    grave
    0.83
    Activations Density 0.012%

    No Known Activations