© 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. 72343
    Prev
    Next
    INDEX
    Explanations

    different, other, another

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

    The neuron flags mentions of devices communicating over networks and related protocol or standard terminology.

    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
     ORIGINAL
    -1.14
    chnet
    -1.02
     rassemb
    -0.95
     finalmente
    -0.95
    尤其
    -0.95
     }}"></
    -0.94
     résister
    -0.93
    脖
    -0.93
    脖子
    -0.93
    beyond
    -0.93
    POSITIVE LOGITS
     different
    1.63
     other
    1.45
     another
    1.38
    Different
    1.35
     others
    1.35
     while
    1.34
     whereas
    1.25
    別の
    1.17
     Different
    1.16
     berbeda
    1.16
    Activations Density 0.054%

    No Known Activations