© 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. 70362
    Prev
    Next
    INDEX
    Explanations

    Give licences, A hybrid, Catholic Church

    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
    尔斯
    -0.99
     conhecida
    -0.98
    V
    -0.96
     OVERVIEW
    -0.96
     elektrische
    -0.96
     âgées
    -0.92
     mitu
    -0.91
    ﺮ
    -0.91
     conocida
    -0.90
    部分が
    -0.90
    POSITIVE LOGITS
     those
    1.28
     with
    1.16
    ！(
    1.13
     fator
    1.12
    Those
    1.12
     贈
    1.07
     méthode
    1.05
     their
    1.02
    cended
    1.02
     mapas
    1.02
    Activations Density 0.025%

    No Known Activations