© 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. 93249
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
    に行ってきました
    -1.08
     which
    -1.08
     where
    -1.07
     кислота
    -1.01
     Offizielle
    -1.00
     ganchillo
    -1.00
    ǂ
    -1.00
    hawatir
    -1.00
    Ayrıca
    -1.00
    佺
    -0.98
    POSITIVE LOGITS
    return
    1.26
    是一
    1.04
     installiert
    0.99
    :
    0.95
    myra
    0.93
    ?
    0.92
    šno
    0.92
     большин
    0.91
    讨厌
    0.91
     отец
    0.91
    Activations Density 0.008%

    No Known Activations