© 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. 8965
    Prev
    Next
    INDEX
    Explanations

    moth of or in

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

    The neuron primarily detects the occurrence of the word “moth,” especially in biological or taxonomic descriptions.

    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
    ቭ
    -2.64
    ۔
    -2.63
    鄚
    -2.36
     inspiradoras
    -2.33
    𖣘
    -2.33
     preciosa
    -2.30
     faldas
    -2.30
    在他的
    -2.25
    　　（
    -2.25
     planas
    -2.17
    POSITIVE LOGITS
    '
    3.00
     the
    2.86
    ',
    2.53
    й
    2.39
    ,
    2.27
     umgangssprach
    2.27
     This
    2.25
     результате
    2.23
    t
    2.22
     Sorten
    2.20
    Activations Density 0.003%

    No Known Activations