© 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. 10-GEMMASCOPE-RES-131K
    7. 105833
    Prev
    Next
    INDEX
    Explanations

    already happened or existing

    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
     simply
    -1.44
    simply
    -1.21
     aspek
    -1.21
    /*!
    -1.21
    Histor
    -1.20
    TERY
    -1.16
     ekster
    -1.16
     is
    -1.15
     rekom
    -1.14
    schwar
    -1.14
    POSITIVE LOGITS
     after
    1.41
    esomeness
    1.36
     sowohl
    1.35
    inerario
    1.33
    iscono
    1.30
    inous
    1.30
     kreeg
    1.26
     FIRST
    1.24
     bahawa
    1.23
     memahami
    1.23
    Activations Density 0.022%

    No Known Activations