© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28322
    Prev
    Next
    INDEX
    Explanations

    technical content and terms

    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
    子さん
    -1.40
    Ⲉ
    -1.27
     or
    -1.26
     große
    -1.24
     this
    -1.24
     reconnaît
    -1.20
     réalise
    -1.17
     out
    -1.16
    vého
    -1.16
     at
    -1.15
    POSITIVE LOGITS
     Hinsicht
    1.32
    搅拌
    1.29
    についても
    1.23
    Hozzáférés
    1.18
     häufiger
    1.17
     ,‬
    1.16
    壁纸
    1.16
     inept
    1.16
    ponses
    1.15
     تقری
    1.15
    Activations Density 0.000%

    No Known Activations