© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71694
    Prev
    Next
    INDEX
    Explanations

    spirit of

    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
     одну
    -2.95
    ↵
    -2.89
    5
    -2.70
     каждый
    -2.56
    >
    -2.50
    什么样的
    -2.48
    跸
    -2.45
    —-
    -2.39
     startling
    -2.36
    部分が
    -2.34
    POSITIVE LOGITS
    }
    2.83
    省市镇
    2.50
     naka
    2.34
    ikiki
    2.31
    🤟
    2.30
    !");
    
    2.28
    weakSelf
    2.27
    كز
    2.27
    <bos>
    2.25
     彈
    2.25
    Activations Density 0.007%

    No Known Activations