© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47949
    Prev
    Next
    INDEX
    Explanations

    components and their relationships

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

    This neuron detects the key noun in “X and another/other X” contrast patterns (e.g. “file and the other file,” “version and another version,” “function and another function,” “menu and another menu,” “class and another class,” “activity and another activity,” “thread and another thread,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     without
    -1.38
     among
    -1.35
     at
    -1.33
     but
    -1.30
     of
    -1.30
     should
    -1.27
     between
    -1.26
     with
    -1.25
     while
    -1.23
     again
    -1.20
    POSITIVE LOGITS
     remarquable
    1.27
    如果
    1.21
     ומש
    1.20
    amental
    1.20
     Czy
    1.20
    妩
    1.19
     pady
    1.16
     обстоятельства
    1.16
    Unione
    1.16
     приве
    1.16
    Activations Density 0.171%

    No Known Activations