© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    there or all

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

    The neuron activates strongly on numeric values and measurements.

    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
    俭
    -1.27
     nikdy
    -1.20
     to
    -1.19
    unächst
    -1.18
     vypl
    -1.16
     later
    -1.11
    谊
    -1.10
     letzt
    -1.07
     cebola
    -1.05
    誼
    -1.05
    POSITIVE LOGITS
     there
    1.95
     everything
    1.46
    THERE
    1.38
     all
    1.24
    everything
    1.22
     هناك
    1.20
     only
    1.20
     wszyscy
    1.17
     सभी
    1.16
     semua
    1.16
    Activations Density 0.072%

    No Known Activations