© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98226
    Prev
    Next
    INDEX
    Explanations

    in terms of

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

    The neuron specifically fires on occurrences of the word “terms,” most strongly when it appears in the phrase “in terms of.”

    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
     durabilidad
    -1.92
    があるので
    -1.84
    </b>
    -1.75
    してます
    -1.75
    なども
    -1.74
     estadía
    -1.70
    ？』
    -1.67
    方法は
    -1.66
    もあるので
    -1.66
     кілька
    -1.65
    POSITIVE LOGITS
     of
    3.78
    s
    1.75
    </h3>
    1.67
    ar
    1.66
     dezelve
    1.63
    ときは
    1.60
     regionale
    1.60
    m
    1.59
    ݯ
    1.57
    臵
    1.56
    Activations Density 0.016%

    No Known Activations