© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123551
    Prev
    Next
    INDEX
    Explanations

    download free content

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

    The neuron detects section‐header and navigation labels related to press/media materials and downloads (e.g. “Press,” “Section,” “Downloads,” “Download,” “Kit”).

    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
    žena
    -1.24
     tecnologias
    -1.24
    通过
    -1.23
    通過
    -1.23
     кто
    -1.22
     ayant
    -1.20
    哪怕
    -1.17
    neus
    -1.15
     who
    -1.14
     tecnológica
    -1.14
    POSITIVE LOGITS
     think
    1.21
     also
    1.17
    isters
    1.14
    њу
    1.13
     for
    1.09
     acceptez
    1.09
    颗粒
    1.09
     aimez
    1.08
     загру
    1.06
     perro
    1.05
    Activations Density 0.077%

    No Known Activations