© 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. 10-GEMMASCOPE-RES-131K
    7. 12429
    Prev
    Next
    INDEX
    Explanations

    end of phrase punctuation

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

    The neuron fires on specialized domain–specific terms and descriptors—technical nouns naming materials, components, measurements, or other precise scientific or architectural features.

    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
     and
    -2.08
          
    -1.52
    z
    -1.47
    f
    -1.43
     our
    -1.43
     variously
    -1.40
    ?
    -1.40
     but
    -1.40
     Our
    -1.39
     bzw
    -1.38
    POSITIVE LOGITS
     informativo
    1.51
     comanda
    1.47
     Compañ
    1.39
    麃
    1.38
     sincero
    1.38
     السياسي
    1.37
    閖
    1.36
     dinding
    1.35
    letzt
    1.34
     minimalista
    1.34
    Activations Density 0.495%

    No Known Activations