© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127729
    Prev
    Next
    INDEX
    Explanations

    original things

    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
    \
    -2.00
    VIATIONS
    -1.80
    =
    -1.73
            
    -1.72
    6
    -1.69
              
    -1.68
    0
    -1.68
    蠖
    -1.64
    eight
    -1.64
     you
    -1.61
    POSITIVE LOGITS
     största
    2.00
     作り方
    1.89
     incorporar
    1.64
    捩
    1.62
    桄
    1.55
     炒め
    1.53
    Tác
    1.52
     Consequently
    1.50
    ?”
    1.45
    ⸒
    1.45
    Activations Density 0.019%

    No Known Activations