© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99095
    Prev
    Next
    INDEX
    Explanations

    Lily followed by other words

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

    The neuron strongly activates on botanical names—especially genus/species names and other plant taxonomic 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
    E
    -2.75
    ↵
    -2.39
    WRENCE
    -2.36
    ↵↵
    -2.33
     leur
    -2.14
    x
    -1.97
     пластик
    -1.95
    il
    -1.94
    直至
    -1.91
     bracing
    -1.89
    POSITIVE LOGITS
    Ꮞ
    2.58
     проєкту
    2.55
    ’
    2.47
    ]
    2.41
    聼
    2.33
    趼
    2.30
    tafogo
    2.23
     получили
    2.23
    ’，
    2.19
     terceiros
    2.19
    Activations Density 0.004%

    No Known Activations