© 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. 28423
    Prev
    Next
    INDEX
    Explanations

    programming and technical contexts

    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
     that
    -1.42
     to
    -1.30
    '=>'
    -1.30
     an
    -1.21
     (
    -1.20
     their
    -1.19
    つづく
    -1.16
    Vorlage
    -1.11
     what
    -1.09
     both
    -1.09
    POSITIVE LOGITS
    ですが
    1.30
    4
    1.27
     regal
    1.27
    6
    1.23
     изменений
    1.23
    5
    1.23
     possib
    1.20
     և
    1.19
     قسمت
    1.18
     goofy
    1.17
    Activations Density 0.046%

    No Known Activations