© 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. 72582
    Prev
    Next
    INDEX
    Explanations

    set within position between

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

    The neuron strongly activates on numeric tokens and measurement values (e.g. distances, counts, quantities).

    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
    ENSATION
    -1.13
     setembro
    -1.12
    rotum
    -1.09
    |[]
    -1.09
    nextProps
    -1.06
     höl
    -1.06
     silikon
    -1.04
    isieren
    -1.03
    thenia
    -1.01
     ekolog
    -1.00
    POSITIVE LOGITS
     ступен
    1.02
     this
    0.96
     umie
    0.94
    这样一个
    0.94
    им
    0.85
    vcpu
    0.84
     countrymen
    0.84
     across
    0.84
     obszar
    0.83
    してみると
    0.82
    Activations Density 0.001%

    No Known Activations