© 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. 102488
    Prev
    Next
    INDEX
    Explanations

    Ferdinand, Rockefeller, Erica, WWF

    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
    憷
    -2.97
    ￨
    -2.66
    紲
    -2.64
    𓐍
    -2.52
    籥
    -2.50
    
    -2.48
    箜
    -2.41
    揠
    -2.36
    をしていた
    -2.36
     démocr
    -2.36
    POSITIVE LOGITS
    {
    3.45
    ↵↵
    2.52
     —
    2.50
    1
    2.47
    at
    2.39
    ,”
    2.34
    4
    2.25
    7
    2.17
            
    2.11
     –
    2.09
    Activations Density 0.002%

    No Known Activations