© 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. 93123
    Prev
    Next
    INDEX
    Explanations

    foreign and domestic topics

    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
     politiche
    -1.32
    ствую
    -1.20
    lography
    -1.19
     santai
    -1.17
    corrhi
    -1.16
     ketat
    -1.16
     indah
    -1.16
    nesses
    -1.16
    ties
    -1.14
    hilation
    -1.14
    POSITIVE LOGITS
     discer
    1.03
     acclaimed
    1.02
     dando
    1.02
     รวม
    1.01
     quintessential
    0.99
     ambigu
    0.98
    內容簡介
    0.97
     unterschiedlich
    0.97
     impreg
    0.96
     existent
    0.96
    Activations Density 0.015%

    No Known Activations