© 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. 33834
    Prev
    Next
    INDEX
    Explanations

    absolute value function

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on tokens that are part of inline mathematical notation (LaTeX/math expressions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    "]').
    -1.06
    .},
    -1.02
     DNA
    -1.00
     tarea
    -0.99
    Generator
    -0.98
    </h3>
    -0.96
     миру
    -0.96
    
    -0.94
     beide
    -0.93
    ?????
    -0.93
    POSITIVE LOGITS
     this
    1.29
     each
    1.20
     our
    1.20
    んですね
    1.11
    んですよね
    1.07
    ọng
    1.04
     Suara
    1.02
     sekarang
    1.01
    のですね
    1.00
    没关系
    0.98
    Activations Density 0.003%

    No Known Activations