© 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. 66279
    Prev
    Next
    INDEX
    Explanations

    other followed by specific types

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

    The neuron specializes in detecting the comparative term “other” when contrasting one group or item with another.

    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
     navigateur
    -1.21
     and
    -1.16
    rowser
    -1.15
    囑
    -1.05
    tivation
    -1.05
    修炼
    -1.00
    istungen
    -0.98
     SHOWS
    -0.98
    licitations
    -0.97
     verzi
    -0.97
    POSITIVE LOGITS
     other
    1.52
     because
    1.27
     it
    1.23
     recent
    1.00
     we
    1.00
     lately
    0.97
     our
    0.95
     modalidades
    0.95
     since
    0.92
     like
    0.89
    Activations Density 0.028%

    No Known Activations