© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69610
    Prev
    Next
    INDEX
    Explanations

    code includes C++ and Java

    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_10/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
     and
    -1.78
    內容簡介
    -1.53
     their
    -1.45
     those
    -1.41
    dacia
    -1.36
     люди
    -1.30
     emanating
    -1.30
    jaguar
    -1.30
     nestled
    -1.30
    льные
    -1.28
    POSITIVE LOGITS
    7
    1.77
    LIKE
    1.63
    4
    1.61
    9
    1.57
     необходимости
    1.54
    NEY
    1.54
    就像
    1.50
    3
    1.50
    we
    1.45
    8
    1.45
    Activations Density 0.010%

    No Known Activations