© 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. 72179
    Prev
    Next
    INDEX
    Explanations

    court cases and arguments

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

    The neuron selectively activates on multi‐digit numeric tokens (e.g. “148”, “136”, “114”) rather than single digits or non‐numeric 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
     attraverso
    -1.09
     Consiglio
    -1.08
     kursi
    -1.03
    SHI
    -1.02
    そして
    -1.00
    JAMIN
    -1.00
     Trọng
    -0.97
     herren
    -0.96
    снов
    -0.94
    INION
    -0.91
    POSITIVE LOGITS
    ándonos
    1.19
    Cevapla
    1.02
    ментом
    1.01
     bestehenden
    0.96
    极为
    0.95
    hrte
    0.93
    だったので
    0.92
    iting
    0.91
     admiten
    0.90
     fremden
    0.90
    Activations Density 0.000%

    No Known Activations