© 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. 20329
    Prev
    Next
    INDEX
    Explanations

    up followed by other words

    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
    in
    -2.91
     for
    -2.41
     of
    -2.30
     by
    -1.91
    >
    -1.85
    like
    -1.84
    のは
    -1.77
    B
    -1.77
     when
    -1.73
    }
    -1.73
    POSITIVE LOGITS
    鹀
    2.42
    囖
    2.27
    𓆉
    2.25
     enthou
    2.25
    
    2.22
    ペーン
    2.22
    彞
    2.16
    Kondisi
    2.14
    ﮨ
    2.13
    媃
    2.13
    Activations Density 0.024%

    No Known Activations