© 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. 127342
    Prev
    Next
    INDEX
    Explanations

    Hogan or Nokia

    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
    7
    -2.56
    ↵
    -2.38
    6
    -2.25
     techniczne
    -2.23
    第一
    -2.22
    4
    -2.22
    '
    -2.19
    新しい
    -2.19
     ด้วย
    -2.11
    閦
    -2.09
    POSITIVE LOGITS
    褙
    2.44
     They
    2.39
     '@/
    2.36
     trouvait
    2.36
     表情
    2.28
    ACIÓN
    2.13
     faisait
    2.11
    𓋼
    2.09
     disait
    2.09
     same
    2.09
    Activations Density 0.008%

    No Known Activations