© 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. 71774
    Prev
    Next
    INDEX
    Explanations

    successful completion of actions

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

    This neuron activates on past-tense or past-participle action words (often capitalized) used in status or log messages to report that an operation completed.

    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
     lorsqu
    -1.23
     כדי
    -1.13
     wzór
    -1.09
    obviously
    -1.09
     heiligen
    -1.09
     propuestas
    -1.08
    
    -1.08
     my
    -1.08
    VERY
    -1.08
    ۱۳
    -1.06
    POSITIVE LOGITS
     successfully
    1.32
     from
    1.28
    !
    1.16
    ()=>{
    1.15
     }),
    1.12
     abstracto
    1.07
    足够的
    1.07
     Nausea
    1.06
    诹
    1.05
     Headache
    1.02
    Activations Density 0.007%

    No Known Activations