© 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. 27373
    Prev
    Next
    INDEX
    Explanations

    contrasting statements

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

    This neuron detects copular “it is/it’s” constructions that introduce a descriptive phrase.

    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
     tersebut
    -1.06
     themselves
    -1.05
    cetta
    -1.04
     których
    -1.00
     Kecil
    -0.99
     oznacza
    -0.98
     jų
    -0.97
     jenen
    -0.96
     această
    -0.93
     törvény
    -0.93
    POSITIVE LOGITS
     you
    1.32
     like
    1.27
     but
    1.20
     that
    1.20
     we
    1.12
     being
    1.02
    chaun
    0.99
     everybody
    0.99
     everyone
    0.95
    が集
    0.94
    Activations Density 0.074%

    No Known Activations