© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    used my understanding

    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
    Zubereitung
    -1.41
     tormenta
    -1.24
     possa
    -1.23
     espere
    -1.21
    lers
    -1.20
    eventually
    -1.20
     decidi
    -1.19
    Kommentare
    -1.18
    ならでは
    -1.18
    usions
    -1.16
    POSITIVE LOGITS
     their
    1.73
     those
    1.37
     of
    1.30
    ງ
    1.30
     my
    1.26
     three
    1.23
    IANGLES
    1.23
     or
    1.16
     markets
    1.16
     five
    1.14
    Activations Density 0.025%

    No Known Activations