© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103477
    Prev
    Next
    INDEX
    Explanations

    qualities, conditions, or limitations

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

    The neuron fires on adjectives or adverbs that convey strong emphasis or intensity (e.g. “indiscriminate,” “highly,” “strictly,” “standardized”).

    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
     fueron
    -1.33
     abitanti
    -1.24
     pequeña
    -1.22
    polate
    -1.21
    不断
    -1.19
     năm
    -1.16
                               
    -1.15
     aliviar
    -1.15
    はこの
    -1.15
     incontri
    -1.12
    POSITIVE LOGITS
     it
    1.41
    especially
    1.21
     redondo
    1.20
     terreno
    1.20
     souci
    1.18
     sekal
    1.17
    ragona
    1.16
     péché
    1.16
     acqua
    1.16
    else
    1.13
    Activations Density 0.392%

    No Known Activations