© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65080
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculus

    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
     wraz
    -0.91
     direita
    -0.89
     весь
    -0.89
     miejsce
    -0.85
     kış
    -0.85
     Mientras
    -0.81
    形で
    -0.81
     maybe
    -0.80
    了下去
    -0.77
     appears
    -0.76
    POSITIVE LOGITS
    LONDON
    0.97
     demokra
    0.89
    reshold
    0.87
    lei
    0.86
    ：……
    0.85
    initData
    0.84
    iação
    0.82
    ESCAPE
    0.81
    acionais
    0.79
     maat
    0.79
    Activations Density 0.005%

    No Known Activations