© 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. 61284
    Prev
    Next
    INDEX
    Explanations

    written by or produced by

    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
     would
    -1.38
     your
    -1.30
    larınız
    -1.30
     widok
    -1.27
    Would
    -1.23
     móg
    -1.23
     titolata
    -1.20
     appunt
    -1.20
    ){$
    -1.18
     esterna
    -1.18
    POSITIVE LOGITS
     They
    1.53
     mereka
    1.52
    та
    1.31
     ovate
    1.31
    there
    1.29
    ाद
    1.21
     from
    1.20
     there
    1.20
     they
    1.18
     with
    1.17
    Activations Density 0.230%

    No Known Activations