© 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. 54259
    Prev
    Next
    INDEX
    Explanations

    qualifiers and descriptions

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

    The neuron identifies mentions of specific descriptive attributes or technical features (i.e. notable properties) of an object or entity.

    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
     großen
    -0.99
    OLOGÍA
    -0.98
     their
    -0.98
     zawsze
    -0.96
     During
    -0.94
     Schicks
    -0.94
     Many
    -0.92
    insegna
    -0.91
     Additionally
    -0.90
     stolet
    -0.90
    POSITIVE LOGITS
     colonne
    1.13
     cosmé
    1.07
    phere
    1.03
     tè
    1.00
     but
    0.98
    зыка
    0.96
     lumine
    0.94
     tempore
    0.94
     Alpes
    0.93
     teraz
    0.93
    Activations Density 0.070%

    No Known Activations