© 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. 34-GEMMASCOPE-RES-131K
    7. 107901
    Prev
    Next
    INDEX
    Explanations

    IDR_MAINFRAME

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

    The neuron fires on isolated numeric tokens (and short numeric identifiers) such as reference or version numbers in technical or code‐like contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     what
    -1.16
    嗚
    -1.12
    What
    -1.02
     but
    -0.97
     Although
    -0.94
    ........
    -0.93
     During
    -0.91
     one
    -0.91
    ینک
    -0.89
    حص
    -0.88
    POSITIVE LOGITS
    ana
    0.93
     ภาพ
    0.91
     Increases
    0.90
    need
    0.87
     opti
    0.85
     يوجد
    0.85
     fiasco
    0.85
    ali
    0.84
     paroi
    0.83
    ographic
    0.82
    Activations Density 0.000%

    No Known Activations