© 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. 2703
    Prev
    Next
    INDEX
    Explanations

    headings and labels

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

    The neuron detects standalone numeric literals (i.e. tokens consisting of numbers).

    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
     serpent
    -0.82
     marta
    -0.79
     diman
    -0.77
     Nego
    -0.77
     Rayon
    -0.76
     rask
    -0.75
     granada
    -0.75
     Serp
    -0.75
     jod
    -0.75
     boya
    -0.74
    POSITIVE LOGITS
     mem
    0.84
     colocar
    0.82
     cubierto
    0.81
     stalwart
    0.77
    óż
    0.76
     recollection
    0.75
    מב
    0.74
     rincón
    0.74
    novo
    0.73
     víz
    0.73
    Activations Density 0.000%

    No Known Activations