© 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. 22-GEMMASCOPE-RES-131K
    7. 38606
    Prev
    Next
    INDEX
    Explanations

    after an event

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

    The main thing this neuron does is spot terms referring to key order‐fulfillment steps (e.g. payment, order receipt, dispatch).

    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
    quickly
    -1.33
    extremely
    -1.29
     extremely
    -1.23
     solamente
    -1.20
     bientôt
    -1.18
     strikingly
    -1.17
    primarily
    -1.17
     banheiro
    -1.17
     rapidement
    -1.15
     astounding
    -1.15
    POSITIVE LOGITS
     or
    2.05
     first
    1.69
     begins
    1.60
     start
    1.52
     begin
    1.52
     your
    1.45
     this
    1.41
     after
    1.40
     primeiros
    1.39
     started
    1.38
    Activations Density 0.030%

    No Known Activations