© 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. 20449
    Prev
    Next
    INDEX
    Explanations

    book, chapter, volume, version, part

    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
    8
    -1.52
     surrounding
    -1.36
    9
    -1.34
     during
    -1.33
     or
    -1.30
     promote
    -1.29
     護
    -1.23
     surroundings
    -1.22
     while
    -1.21
     Zwar
    -1.19
    POSITIVE LOGITS
    ཥ
    1.50
    ⸻
    1.34
    糴
    1.32
     』
    1.31
     />";
    1.29
     exhi
    1.25
    least
    1.20
    臵
    1.20
    ཌ
    1.20
    er
    1.20
    Activations Density 0.086%

    No Known Activations