© 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. 41478
    Prev
    Next
    INDEX
    Explanations

    WE

    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
     și
    -2.56
     of
    -2.30
    O
    -2.14
    in
    -2.13
     và
    -2.09
    ss
    -2.08
     और
    -2.08
    na
    -2.08
    }
    -2.06
     realising
    -2.05
    POSITIVE LOGITS
    0
    2.66
    ⡪
    2.58
     Whether
    2.38
    却又
    2.25
    觊
    2.08
    Недостатки
    2.06
    enseignements
    2.05
    ключение
    2.03
    當時
    1.98
     It
    1.96
    Activations Density 0.057%

    No Known Activations