© 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. 72775
    Prev
    Next
    INDEX
    Explanations

    code structures and questions

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

    The neuron strongly responds to standalone numeric literals (integer tokens) in the text.

    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
     its
    -1.01
     sebuah
    -0.89
     pistes
    -0.87
    quela
    -0.86
     maak
    -0.86
     fãs
    -0.86
     dunkel
    -0.85
    пі
    -0.85
     itself
    -0.85
    opies
    -0.82
    POSITIVE LOGITS
    '])){
    1.01
    valier
    0.97
     vermutlich
    0.93
     when
    0.93
     histories
    0.90
    Numerous
    0.88
    pués
    0.88
    riere
    0.87
     numerous
    0.86
     außerord
    0.86
    Activations Density 0.000%

    No Known Activations