© 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. 68469
    Prev
    Next
    INDEX
    Explanations

    states of being or conditions

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

    The neuron responds to uses of the adjective “different,” flagging whenever something is described as being different.

    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
    -1.43
     kekinian
    -1.24
     hosszú
    -1.23
     При
    -1.20
    啰
    -1.20
     szükséges
    -1.17
     által
    -1.14
     illet
    -1.13
    где
    -1.13
     ПО
    -1.13
    POSITIVE LOGITS
     you
    1.25
     like
    1.06
     only
    1.05
     or
    1.05
    /
    1.05
     university
    1.00
     either
    1.00
     its
    0.99
     ofrece
    0.98
     didn
    0.98
    Activations Density 0.061%

    No Known Activations