© 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. 70886
    Prev
    Next
    INDEX
    Explanations

    number 4

    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
    ↵
    -2.83
     that
    -2.14
     the
    -2.14
    </b>
    -1.98
    ๖
    -1.96
     beserta
    -1.94
     енер
    -1.91
    </h2>
    -1.88
     ketika
    -1.85
    はコチラ
    -1.85
    POSITIVE LOGITS
    4
    2.75
    鲵
    2.44
    都不知道
    2.39
    愎
    2.38
    ⧼
    2.34
    𓇼
    2.33
    5
    2.28
    ise
    2.27
    煳
    2.25
    x
    2.22
    Activations Density 0.235%

    No Known Activations