© 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. 11696
    Prev
    Next
    INDEX
    Explanations

    literature

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

    The neuron specifically fires on mentions of “literature” (and its adjectival form “literary”).

    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
     ваше
    -2.88
    迅速
    -2.59
    樒
    -2.47
    埽
    -2.42
    ing
    -2.39
    琹
    -2.34
    熥
    -2.33
    怱
    -2.31
    在我
    -2.30
    仍然
    -2.28
    POSITIVE LOGITS
    .
    5.38
    ).
    2.42
     optimizar
    2.41
    髏
    2.39
     damska
    2.36
     })
    2.30
    」
    2.30
     That
    2.28
     Hinsicht
    2.27
    ”،
    2.27
    Activations Density 0.009%

    No Known Activations