© 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. 119051
    Prev
    Next
    INDEX
    Explanations

    exponentiation, subtraction, multiplication, division

    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
     !=
    -1.02
    rscheinlich
    -0.91
    店で
    -0.89
     $-
    -0.84
     sadece
    -0.83
    Lato
    -0.80
    ционные
    -0.79
     *=
    -0.77
     /=
    -0.77
     ≠
    -0.77
    POSITIVE LOGITS
     plus
    2.22
     minus
    2.14
     times
    2.09
     multiplied
    1.94
    Plus
    1.90
    PLUS
    1.83
    plus
    1.81
    minus
    1.65
     PLUS
    1.64
     Plus
    1.55
    Activations Density 0.091%

    No Known Activations