© 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. 127427
    Prev
    Next
    INDEX
    Explanations

    fatal error or consequence

    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
    珦
    -2.59
    ܜ
    -2.03
     ก็
    -2.03
    Ᏻ
    -2.03
    蓠
    -2.02
    糴
    -2.00
     explicado
    -1.96
     participado
    -1.92
    埽
    -1.92
    嵛
    -1.88
    POSITIVE LOGITS
    1
    2.98
    8
    2.80
    3
    2.45
    7
    2.41
    2
    2.25
    4
    2.22
    To
    1.94
    With
    1.92
    T
    1.88
    And
    1.87
    Activations Density 0.002%

    No Known Activations