© 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. 68120
    Prev
    Next
    INDEX
    Explanations

    System.Data namespaces

    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
     suí
    -1.30
     barato
    -1.29
    癀
    -1.26
    のおすすめ
    -1.22
     personnalisé
    -1.20
    無し
    -1.20
     zape
    -1.20
     its
    -1.20
    ヒ
    -1.19
    づけ
    -1.18
    POSITIVE LOGITS
     &
    1.59
    з
    1.22
     nemesis
    1.14
    værk
    1.14
    āti
    1.13
    これも
    1.13
    1.11
     folgendes
    1.11
    极为
    1.08
    سية
    1.06
    Activations Density 0.002%

    No Known Activations