© 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. 9528
    Prev
    Next
    INDEX
    Explanations

    I consider / I may

    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
     السياس
    -1.20
     whatnot
    -1.16
    ですが
    -1.16
    があります
    -1.10
    liday
    -1.09
    ¹)
    -1.09
    がございます
    -1.06
    𖡼
    -1.06
     seguintes
    -1.05
     tačiau
    -1.05
    POSITIVE LOGITS
     they
    1.41
     not
    1.27
    ようになって
    1.24
    為に
    1.21
     like
    1.21
    ようになりました
    1.15
     I
    1.13
    時も
    1.12
     no
    1.04
    わけではない
    1.04
    Activations Density 0.099%

    No Known Activations