© 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. 65986
    Prev
    Next
    INDEX
    Explanations

    exam cram, Supra Shoes, Factory Pty, [Minimal, Hollywood Blvd, Stochastic separation

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

    This neuron detects numeric tokens or multi‐digit sequences (i.e. numbers).

    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
    
    -1.12
    assertThrows
    -1.08
    兩人
    -1.07
    EdgeInsets
    -1.06
    してしまった
    -1.05
    érables
    -1.02
    ómico
    -0.99
    诙
    -0.99
    ilarities
    -0.99
     raíces
    -0.99
    POSITIVE LOGITS
     stiller
    0.96
     great
    0.94
     Sicher
    0.91
    
    0.90
    d
    0.89
     pantal
    0.88
     siff
    0.88
    se
    0.87
    굉
    0.86
     saad
    0.85
    Activations Density 0.001%

    No Known Activations