© 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. 34-GEMMASCOPE-RES-131K
    4. 107428
    Prev
    Next
    INDEX
    Explanations

    qlengine or cqlengine

    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_34/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
    揉
    -0.89
    ('#
    -0.70
    なさい
    -0.69
    abetta
    -0.68
     crossed
    -0.67
    efes
    -0.67
    COL
    -0.66
     J
    -0.65
    taj
    -0.64
    ein
    -0.64
    POSITIVE LOGITS
     engine
    1.78
    engine
    1.67
     engines
    1.34
     Engine
    1.34
    Engine
    1.34
    ENGINE
    1.22
     ENGINE
    1.21
     Engines
    1.19
    引擎
    1.04
    engines
    0.99
    Activations Density 0.022%

    No Known Activations