© 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. 22-GEMMASCOPE-RES-131K
    7. 12489
    Prev
    Next
    INDEX
    Explanations

    view and LinearLayout elements

    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_22/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
    return
    -1.40
    have
    -1.27
    m
    -1.24
     verranno
    -1.23
    成功
    -1.20
     furono
    -1.17
     kayna
    -1.13
    SpringRunner
    -1.13
    \
    -1.11
     its
    -1.10
    POSITIVE LOGITS
    ='';
    1.28
     berätt
    1.19
    的部分
    1.18
    𝄇
    1.13
     новая
    1.13
     vigencia
    1.13
     gewöhnlich
    1.13
     condol
    1.13
    =[];
    1.12
     аккура
    1.11
    Activations Density 0.003%

    No Known Activations