© 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. 128555
    Prev
    Next
    INDEX
    Explanations

    The neuron spots evaluative comparative/superlative opinion phrases—especially “X is the best”–style praise statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    comparison and uniqueness

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Lmfao
    -1.12
    Hahah
    -1.02
     wtedy
    -0.97
    Hahahahaha
    -0.93
    setDo
    -0.93
     memasukkan
    -0.91
    Both
    -0.90
     mendukung
    -0.90
    どちらも
    -0.89
    Awwww
    -0.89
    POSITIVE LOGITS
     others
    1.41
     among
    1.24
     unique
    1.17
     uniqueness
    1.15
     amongst
    1.15
    Unique
    1.11
    others
    1.10
     differentiation
    1.02
     comparative
    1.02
    unique
    1.01
    Activations Density 0.060%

    No Known Activations