© 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. 129731
    Prev
    Next
    INDEX
    Explanations

    return 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
    ということを
    -2.11
     большую
    -2.09
    ac
    -2.00
    那我
    -1.96
     盖
    -1.95
     это
    -1.93
    悪く
    -1.87
    背影
    -1.86
     iguales
    -1.83
    哎呀
    -1.83
    POSITIVE LOGITS
     to
    2.88
    有
    2.36
    Ⲉ
    2.34
     realizará
    2.30
    最早
    2.25
     Certificado
    2.22
    =’
    2.20
    stoffen
    2.17
     Crédito
    2.17
     griego
    2.16
    Activations Density 0.027%

    No Known Activations