© 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. 71215
    Prev
    Next
    INDEX
    Explanations

    Attn:

    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
     нее
    -1.29
    増えて
    -1.27
    álna
    -1.27
     campañas
    -1.21
     Besitz
    -1.19
     wou
    -1.19
    であり
    -1.19
     Ortsteil
    -1.18
    ים
    -1.18
     morir
    -1.16
    POSITIVE LOGITS
     then
    1.61
     to
    1.49
    —¡
    1.41
     Informações
    1.40
     ίδ
    1.34
    then
    1.31
    нией
    1.31
    found
    1.31
    still
    1.30
    tifiable
    1.28
    Activations Density 0.159%

    No Known Activations