© 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. 11939
    Prev
    Next
    INDEX
    Explanations

    aircraft, rotor, drops, thermal

    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
     nawet
    -1.66
    Also
    -1.63
     Incluso
    -1.51
     Also
    -1.45
     their
    -1.38
    Even
    -1.33
    Surprisingly
    -1.30
    ثم
    -1.29
    chtige
    -1.27
    遼
    -1.27
    POSITIVE LOGITS
     forState
    1.56
    \
    1.49
    ksiyon
    1.25
     faça
    1.24
     hagan
    1.22
     sejam
    1.18
     inond
    1.18
    na
    1.18
     セール
    1.18
     только
    1.17
    Activations Density 0.054%

    No Known Activations