© 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. 47684
    Prev
    Next
    INDEX
    Explanations

    relevant

    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
    ˃
    -1.45
    ₦
    -1.41
     as
    -1.33
    kében
    -1.32
    asanjo
    -1.32
     motivos
    -1.30
     verdaderos
    -1.27
    珅
    -1.27
     schon
    -1.27
    idespread
    -1.26
    POSITIVE LOGITS
     میکنم
    1.39
     而
    1.38
     immor
    1.32
     umbre
    1.21
     geomet
    1.17
     iveco
    1.16
     credo
    1.16
     notizia
    1.16
     for
    1.15
     ครับ
    1.15
    Activations Density 0.076%

    No Known Activations