© 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. 33556
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and notation

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

    This neuron is triggered by numeric tokens (digits or numbers) 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
     from
    -1.16
    ناه
    -0.97
    omethyl
    -0.94
     şimdi
    -0.93
     razie
    -0.93
    apnews
    -0.91
    bullets
    -0.90
    llten
    -0.89
    DebuggerNonUser
    -0.89
    st
    -0.88
    POSITIVE LOGITS
     לאחר
    1.17
     メル
    1.00
     sparring
    0.93
     klasik
    0.93
    In
    0.93
    w
    0.89
    そこは
    0.89
     moks
    0.88
    fycat
    0.88
    依靠
    0.88
    Activations Density 0.005%

    No Known Activations