© 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. 22-GEMMASCOPE-RES-131K
    7. 15619
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

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

    The neuron responds to numeric tokens—both digits and spelled‐out 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_22/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
     about
    -0.99
     hundreds
    -0.98
    ladı
    -0.93
     both
    -0.92
     sentimentos
    -0.91
     sufficiently
    -0.90
     turquesa
    -0.88
     adequado
    -0.87
    accompagnement
    -0.87
    apprentissage
    -0.85
    POSITIVE LOGITS
     including
    1.09
    issent
    1.08
    Including
    1.07
    naire
    1.03
     Including
    1.02
     включая
    0.99
     dahil
    0.99
    fillText
    0.98
     คือ
    0.94
     страхо
    0.93
    Activations Density 0.061%

    No Known Activations