© 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. 63867
    Prev
    Next
    INDEX
    Explanations

    astronomical object names and coordinates

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

    The neuron fires on long sequences of digits—multi-digit numeric identifiers (e.g. catalog numbers, coordinates, or other large numeric codes).

    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
    Empereur
    -0.87
    antel
    -0.86
     lettres
    -0.84
     SOUTHERN
    -0.83
    idées
    -0.83
    uchu
    -0.82
     antara
    -0.82
    ardez
    -0.82
     stadt
    -0.82
     macam
    -0.82
    POSITIVE LOGITS
    Prairie
    0.76
    锁
    0.75
    Prun
    0.73
    Onion
    0.73
    Rams
    0.73
    ージャ
    0.71
     Alkaline
    0.71
    rane
    0.71
     erklären
    0.71
     EFF
    0.70
    Activations Density 0.001%

    No Known Activations