© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78802
    Prev
    Next
    INDEX
    Explanations

    mathematical notation including 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_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
     />
    -1.05
    ykite
    -0.91
     /
    -0.91
    ;
    
    -0.90
    ΙΝ
    -0.90
    \(
    -0.90
    Rnd
    -0.88
    
    -0.86
     /$
    -0.86
    ksiä
    -0.86
    POSITIVE LOGITS
     Aseg
    1.01
    ising
    0.98
    してる
    0.97
    Doesn
    0.96
    Want
    0.96
    Lots
    0.90
    sieme
    0.88
     gefährlich
    0.87
     společ
    0.87
     tappa
    0.87
    Activations Density 0.400%

    No Known Activations