© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103571
    Prev
    Next
    INDEX
    Explanations

    pronouns and 'button' followed by prepositions

    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
     reacties
    -1.34
     kağı
    -1.29
     pracę
    -1.28
     sonrası
    -1.27
     satış
    -1.26
     działanie
    -1.22
    }]{
    -1.20
    .}(
    -1.19
     essas
    -1.18
     accordo
    -1.18
    POSITIVE LOGITS
     different
    1.43
    봤
    1.20
     not
    1.18
     oraz
    1.13
     some
    1.12
     diferite
    1.12
     today
    1.10
    鉛筆
    1.05
     all
    1.03
     as
    1.02
    Activations Density 0.154%

    No Known Activations