© 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. 62935
    Prev
    Next
    INDEX
    Explanations

    price per sq ft

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

    the neuron activates on numeric tokens, picking out numbers, percentages, and other statistical or measurement values 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
     शुर
    -0.93
    OBJETIVOS
    -0.93
    SALUD
    -0.91
    Poids
    -0.91
    Horário
    -0.90
    RESULTADOS
    -0.89
    Berat
    -0.89
    SÍ
    -0.89
    Lain
    -0.89
    struzioni
    -0.88
    POSITIVE LOGITS
     Days
    1.49
     days
    1.42
     median
    1.39
    Days
    1.38
    days
    1.30
    median
    1.19
     market
    1.10
     DAYS
    1.08
    Median
    0.99
     Est
    0.95
    Activations Density 0.002%

    No Known Activations