© 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. 10-GEMMASCOPE-RES-131K
    4. 80673
    Prev
    Next
    INDEX
    Explanations

    access tokens and keys

    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>
    -2.63
    も含
    -2.42
    </strong>
    -2.30
     
    -2.16
     he
    -2.16
    の存在
    -2.14
     of
    -2.11
    ни
    -1.98
     his
    -1.95
    などに
    -1.91
    POSITIVE LOGITS
    Penjelasan
    2.34
    状况
    2.30
    However
    2.22
    Зачем
    2.22
    Tujuan
    2.20
    ſchen
    2.17
    Можно
    2.17
    There
    2.16
    Dengan
    2.14
    ثم
    2.14
    Activations Density 0.013%

    No Known Activations