© 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. 39389
    Prev
    Next
    INDEX
    Explanations

    processes and conditions

    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
     gethan
    -1.16
    うわ
    -1.11
    場合には
    -1.09
    Ingrédients
    -1.08
    éphane
    -1.07
     музы
    -1.06
     stadt
    -1.02
    zapatillas
    -1.02
     résult
    -1.02
     Kartoff
    -1.01
    POSITIVE LOGITS
     keberadaan
    1.21
    ENZO
    1.14
     devices
    1.13
    جار
    1.08
     while
    1.07
     ervaring
    1.05
    ículos
    1.04
     
    1.04
    itability
    1.02
    кость
    1.02
    Activations Density 0.262%

    No Known Activations