© 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. 12471
    Prev
    Next
    INDEX
    Explanations

    Start of questions or lists

    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
    actually
    -1.12
     Gouver
    -1.02
     actionTypes
    -1.00
    WL
    -1.00
     tênis
    -0.97
    斯基
    -0.96
     getRole
    -0.95
     havet
    -0.94
     生産
    -0.94
     outra
    -0.94
    POSITIVE LOGITS
     and
    1.26
    Martina
    1.02
     didn
    0.96
    เริ่ม
    0.92
    MYSQL
    0.89
     started
    0.85
    seteq
    0.84
    Реги
    0.84
    nių
    0.83
    积
    0.82
    Activations Density 0.000%

    No Known Activations