© 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. 66687
    Prev
    Next
    INDEX
    Explanations

    no X is like Y

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

    This neuron detects expressions stating that “no two” (or “not two”) things are the same or alike—that is, negated statements of identicality.

    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
     FUTURE
    -1.00
     plutôt
    -0.96
     abstrak
    -0.95
     gari
    -0.94
    rather
    -0.93
    🪲
    -0.91
     rather
    -0.90
     klien
    -0.90
    IPAC
    -0.89
    IDER
    -0.89
    POSITIVE LOGITS
     any
    1.48
     anywhere
    1.32
     anyone
    1.18
     same
    1.07
     anything
    1.02
     nor
    0.96
     anymore
    0.94
     anybody
    0.90
     ANY
    0.87
     Always
    0.86
    Activations Density 0.043%

    No Known Activations