© 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. 22-GEMMASCOPE-RES-131K
    7. 65000
    Prev
    Next
    INDEX
    Explanations

    performing actions and their consequences

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

    The neuron lights up on key content verbs (especially main, non‐auxiliary actions) in a sentence.

    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
     also
    -1.21
     một
    -1.20
     
    -0.99
     shimmering
    -0.98
    一个
    -0.96
     whimsical
    -0.96
     quintessential
    -0.96
     breathtaking
    -0.96
     exhilarating
    -0.96
     commencer
    -0.95
    POSITIVE LOGITS
     this
    1.91
     these
    1.55
     most
    1.41
    atürk
    1.30
     the
    1.20
     найбіль
    1.10
    mability
    1.08
    最为
    1.07
    Postup
    1.06
     those
    1.04
    Activations Density 0.022%

    No Known Activations