© 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. 10-GEMMASCOPE-RES-131K
    7. 67559
    Prev
    Next
    INDEX
    Explanations

    assigned duties

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

    The neuron activates on instances of “charged with” or “tasked with” (i.e. past-participial verbs followed by “with” that assign an accusation or responsibility).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     мои
    -1.53
     valioso
    -1.51
     Zuhause
    -1.50
     berücksichtigt
    -1.48
     japonais
    -1.44
     verwal
    -1.43
    僦
    -1.43
     ersche
    -1.43
     migrantes
    -1.41
    ."
    -1.39
    POSITIVE LOGITS
    at
    1.70
     Nachdem
    1.55
     були
    1.53
    isateurs
    1.49
     This
    1.48
    銪
    1.38
     tasked
    1.37
     not
    1.33
     be
    1.31
     Not
    1.31
    Activations Density 0.018%

    No Known Activations