© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82539
    Prev
    Next
    INDEX
    Explanations

    Air India Blizzard Share

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

    The neuron responds strongly to numeric tokens (e.g. digits or numeric literals).

    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
     MAINTENANCE
    -0.81
    contamination
    -0.78
     bailarina
    -0.75
    contaminated
    -0.75
     CARBON
    -0.75
    afari
    -0.74
     Regione
    -0.73
    QObject
    -0.73
    ńskich
    -0.73
    Länge
    -0.72
    POSITIVE LOGITS
    Diagonal
    0.94
     CCM
    0.83
     CM
    0.82
     Diagonal
    0.80
     diagonal
    0.79
     annot
    0.78
     CLP
    0.78
     BN
    0.77
     白色
    0.75
     Mol
    0.73
    Activations Density 0.004%

    No Known Activations