© 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. 10-GEMMASCOPE-RES-131K
    4. 20424
    Prev
    Next
    INDEX
    Explanations

    section titles and questions

    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
     This
    -1.55
     They
    -1.51
     of
    -1.45
    ulage
    -1.30
    IZE
    -1.22
     étrang
    -1.22
     diversité
    -1.20
     which
    -1.17
    かもし
    -1.17
     that
    -1.16
    POSITIVE LOGITS
     gyerek
    1.55
    "../
    1.53
    asics
    1.52
    CHREIB
    1.46
    madrid
    1.45
    eapple
    1.45
    🧵
    1.44
    vinilo
    1.41
     család
    1.38
     '
    1.38
    Activations Density 0.011%

    No Known Activations