© 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. 73257
    Prev
    Next
    INDEX
    Explanations

    junto followed complemented

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

    The neuron strongly activates on common English function words (e.g. is, was, it, to, their) rather than content words.

    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
    хами
    -0.95
     which
    -0.93
     aboli
    -0.88
    kiyor
    -0.85
     국가
    -0.85
    那时候
    -0.82
    金沢
    -0.81
    igera
    -0.80
     tästä
    -0.77
    Specifica
    -0.76
    POSITIVE LOGITS
     followed
    1.24
     replaced
    1.17
     junto
    1.14
    followed
    1.07
     plus
    1.02
     complemented
    0.98
     preceded
    0.96
     supplemented
    0.95
     mellett
    0.94
     zusammen
    0.92
    Activations Density 0.095%

    No Known Activations