© 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. 75582
    Prev
    Next
    INDEX
    Explanations

    prosecution and methylation

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

    The neuron fires on nouns ending in the suffix “-tion” (e.g. prosecution, methylation).

    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
    When
    -4.63
    While
    -4.44
    Since
    -4.41
    With
    -4.28
    After
    -4.25
    It
    -4.22
    Although
    -4.19
    There
    -4.16
    According
    -4.16
    During
    -4.13
    POSITIVE LOGITS
    鑁
    2.63
    ᠁
    2.50
    ſſi
    2.47
    ről
    2.45
    ſam
    2.44
    itic
    2.42
    ⃤
    2.42
    </b>
    2.42
    鹩
    2.42
    ೢ
    2.41
    Activations Density 0.018%

    No Known Activations