© 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. 101951
    Prev
    Next
    INDEX
    Explanations

    transcription or transcribed text

    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
    ſelf
    -2.16
    ものに
    -2.06
    ㉖
    -2.03
    樒
    -2.00
    饪
    -1.98
    ſu
    -1.96
     andere
    -1.91
    {~
    -1.89
    鯪
    -1.87
     seus
    -1.86
    POSITIVE LOGITS
    i
    2.86
    桖
    2.03
    酲
    2.00
    ୈ
    1.99
     celeb
    1.91
     Oils
    1.91
    ＂
    1.90
    怎么回事
    1.87
    步驟
    1.87
    늄
    1.85
    Activations Density 0.017%

    No Known Activations