© 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. 10218
    Prev
    Next
    INDEX
    Explanations

    time followed by text

    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
    \
    -1.57
    also
    -1.54
    Também
    -1.46
    paigns
    -1.45
    2
    -1.41
    等人
    -1.40
     Ahnung
    -1.37
     також
    -1.36
     is
    -1.36
    那天
    -1.35
    POSITIVE LOGITS
    鱻
    1.66
     monstre
    1.56
    teht
    1.47
    IDADE
    1.45
     oiseau
    1.41
     toalla
    1.41
    歘
    1.40
    挾
    1.38
     each
    1.37
     plancher
    1.35
    Activations Density 0.015%

    No Known Activations