© 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. 977
    Prev
    Next
    INDEX
    Explanations

    technical acronyms and protocols

    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
     why
    -1.66
    两个
    -1.66
    甚至
    -1.65
     даже
    -1.58
     nawet
    -1.55
     others
    -1.54
     worse
    -1.53
    戋
    -1.51
     munc
    -1.50
    _
    -1.49
    POSITIVE LOGITS
    <td>
    1.66
    TAWA
    1.55
     or
    1.45
     tikai
    1.45
     całej
    1.39
     확인함
    1.37
     plátano
    1.34
    чил
    1.34
    bbero
    1.34
    沇
    1.33
    Activations Density 0.180%

    No Known Activations