© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66458
    Prev
    Next
    INDEX
    Explanations

    designed specifically for

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

    This neuron detects imperative-choice instructions—especially “Choose a … that …” style recommendations.

    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
    yship
    -1.18
     there
    -1.13
     basically
    -1.12
    tacular
    -1.09
    achio
    -1.07
     BitmapFactory
    -1.07
    Zdrav
    -1.06
     hispan
    -1.05
     "../../../../
    -1.04
    >+</
    -1.02
    POSITIVE LOGITS
     your
    1.41
    preferably
    1.23
     ít
    1.23
     or
    1.20
     хотя
    1.14
     nicht
    1.05
     almeno
    1.05
     preferably
    1.05
    至少
    1.03
     advertised
    1.02
    Activations Density 0.024%

    No Known Activations