© 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. 22-GEMMASCOPE-RES-131K
    7. 39260
    Prev
    Next
    INDEX
    Explanations

    began to

    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
    стій
    -1.28
     cuchara
    -1.25
     sprawd
    -1.21
    ější
    -1.20
     cuarent
    -1.17
     使っ
    -1.14
     that
    -1.13
     alojamientos
    -1.12
     those
    -1.09
    ûn
    -1.06
    POSITIVE LOGITS
     to
    2.34
    waitUntil
    1.05
    тическое
    1.03
     empiezan
    1.00
     начинают
    0.98
     أكثر
    0.98
     papillon
    0.97
    Menurutnya
    0.96
    蝴蝶
    0.95
    thig
    0.95
    Activations Density 0.017%

    No Known Activations