© 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. 22-GEMMASCOPE-RES-131K
    7. 67474
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     pará
    -1.08
     самое
    -1.07
     amor
    -1.07
    êques
    -1.06
     el
    -1.06
     of
    -1.05
    軋
    -1.04
    檜
    -1.04
     titu
    -1.02
    ntä
    -1.02
    POSITIVE LOGITS
     itong
    1.16
    핌
    1.04
    fahrzeuge
    1.00
    atric
    1.00
     gewal
    0.99
     られる
    0.99
     zijne
    0.96
     geholfen
    0.95
     veículo
    0.95
     ಮತ್ತು
    0.95
    Activations Density 0.005%

    No Known Activations