© 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. 63215
    Prev
    Next
    INDEX
    Explanations

    /* comments and code delimiters

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

    This neuron detects numeric constants—sequences of digits—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_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
     København
    -0.83
     hotell
    -0.82
    JPL
    -0.81
    ͵
    -0.81
    ాన
    -0.79
     \#:
    -0.79
    ̝
    -0.78
    😤
    -0.77
    JLabel
    -0.77
     丹
    -0.77
    POSITIVE LOGITS
    控え
    0.83
    などは
    0.82
     alas
    0.80
    honestly
    0.79
    appareil
    0.79
     τό
    0.77
    偏偏
    0.77
    Piece
    0.77
     ari
    0.75
    门
    0.75
    Activations Density 0.001%

    No Known Activations