© 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. 29071
    Prev
    Next
    INDEX
    Explanations

    artificial or simulated terms

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

    The neuron fires on occurrences of the prefix “pseudo” in compound or hyphenated terms.

    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
    熥
    -2.48
    ?"
    -2.48
    ꜆
    -2.47
    甃
    -2.34
    !"
    -2.33
     suasana
    -2.33
    蹋
    -2.22
     tidak
    -2.22
    ."
    -2.17
    珦
    -2.16
    POSITIVE LOGITS
    er
    3.20
    ↵
    3.09
    ’
    2.59
     &
    2.55
    ↵↵
    2.50
    <bos>
    2.41
     “
    2.31
    垟
    2.28
     
    2.28
     disgusting
    2.28
    Activations Density 0.003%

    No Known Activations