© 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. 33061
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     this
    -1.02
     it
    -0.93
     materiais
    -0.92
    しに
    -0.91
    Spécifications
    -0.90
     uvas
    -0.90
    DeclareMath
    -0.85
    と話
    -0.85
    interceptor
    -0.83
     saludos
    -0.83
    POSITIVE LOGITS
     població
    0.96
     theyre
    0.90
     They
    0.89
    without
    0.89
    they
    0.88
    ケティング
    0.88
     they
    0.87
    🦬
    0.85
    ävän
    0.85
    퐿
    0.83
    Activations Density 0.022%

    No Known Activations