© 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. 11192
    Prev
    Next
    INDEX
    Explanations

    biblical chapters and verses

    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
     LoginComponent
    -1.12
    υνα
    -1.11
    关卡
    -1.07
    外部リンク
    -1.06
    undidad
    -1.02
    pilih
    -1.02
    最新的
    -1.01
     gewünschten
    -0.99
     &
    -0.96
     correspondingly
    -0.95
    POSITIVE LOGITS
     informática
    1.27
    =“
    1.16
     armadura
    1.14
    ortal
    1.13
     Scritto
    1.12
     aceit
    1.11
    ῖς
    1.10
     Descubre
    1.10
     MEMORIAL
    1.10
     bordado
    1.09
    Activations Density 0.004%

    No Known Activations