© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73680
    Prev
    Next
    INDEX
    Explanations

    delivering or licensing information

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

    The neuron responds to service‐oriented action words—especially verbs like “delivering,” “ship,” and “licenses”—that describe providing shipping, delivery, or licensing.

    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
     first
    -1.34
     we
    -1.33
     I
    -1.26
     at
    -1.25
     required
    -1.24
     long
    -1.22
     there
    -1.20
     appropriate
    -1.20
     it
    -1.19
     one
    -1.18
    POSITIVE LOGITS
    さてさて
    1.53
     *++
    1.49
    というわけで
    1.35
    ―――
    1.34
     dégust
    1.33
     choisis
    1.23
    そういえば
    1.23
    ●●
    1.23
     تض
    1.23
    almost
    1.22
    Activations Density 0.001%

    No Known Activations