© 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. 10-GEMMASCOPE-RES-131K
    7. 61482
    Prev
    Next
    INDEX
    Explanations

    mixed language, code, and punctuation

    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_10/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
    </h1>
    -2.77
    醍
    -2.31
    橦
    -2.30
    甞
    -2.16
    铤
    -2.14
    𓋼
    -2.11
    掟
    -2.09
    
    -2.09
    ꜆
    -2.02
    憮
    -2.02
    POSITIVE LOGITS
    他
    2.47
    6
    2.42
    1
    2.39
    8
    2.34
    </em>
    2.31
    7
    2.28
    .”
    2.28
    2
    2.25
    4
    2.25
    s
    2.05
    Activations Density 0.054%

    No Known Activations