© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32562
    Prev
    Next
    INDEX
    Explanations

    various features

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

    The neuron responds to numeric and quantitative expressions—digits, measurements, counts, and other numeric data.

    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
    Because
    -1.16
     Because
    -1.10
     very
    -1.05
     this
    -1.02
     because
    -0.99
     дуже
    -0.99
    交付
    -0.94
     очень
    -0.92
     inilah
    -0.92
     Когда
    -0.91
    POSITIVE LOGITS
    ⚢
    1.00
    voie
    0.95
     crea
    0.94
     FEATURE
    0.91
     biet
    0.91
    riert
    0.90
    thique
    0.89
    various
    0.88
     diversos
    0.87
    (/[
    0.87
    Activations Density 0.005%

    No Known Activations