© 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. 93182
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases

    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
     to
    -1.25
     even
    -1.13
    和
    -1.09
     вона
    -1.05
    jshint
    -1.04
     інформа
    -1.03
    乃至
    -1.02
    ilibr
    -0.98
     навіть
    -0.98
     Yet
    -0.96
    POSITIVE LOGITS
     tersebut
    1.14
     člověk
    1.14
    說道
    1.14
    seitigen
    1.13
     HomeScreen
    1.10
     aidé
    1.09
    還在
    1.05
    ⽬
    1.05
     fomentar
    1.05
    した場合
    1.05
    Activations Density 0.032%

    No Known Activations