© 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. 72997
    Prev
    Next
    INDEX
    Explanations

    fields and open land

    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
     હ
    -1.37
     已
    -1.34
     leur
    -1.34
     сковоро
    -1.34
    тус
    -1.33
    ERÍA
    -1.31
     ਮ
    -1.30
    rive
    -1.29
    (/^
    -1.28
     Polls
    -1.28
    POSITIVE LOGITS
    '
    1.70
    )
    1.63
    "
    1.44
     irmãos
    1.36
     acoged
    1.31
    껍
    1.29
     namorados
    1.27
     "
    1.23
     something
    1.22
    蹰
    1.20
    Activations Density 0.055%

    No Known Activations