© 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. 34-GEMMASCOPE-RES-131K
    4. 119384
    Prev
    Next
    INDEX
    Explanations

    Spanish and Portuguese words

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

    The neuron is primarily responding to punctuation tokens (particularly sentence‐ending marks like periods and question marks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     of
    -1.11
     mụn
    -0.98
    ままで
    -0.97
     anun
    -0.91
     Desain
    -0.91
     dekoratif
    -0.91
    sommer
    -0.90
     好き
    -0.90
     becauſe
    -0.90
    🥀
    -0.89
    POSITIVE LOGITS
     the
    1.34
     exist
    1.19
     are
    1.15
    があり
    1.07
     comprise
    1.06
     its
    1.03
     두
    1.02
     세
    1.01
    并在
    0.97
     encontrada
    0.97
    Activations Density 0.012%

    No Known Activations