© 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. 39943
    Prev
    Next
    INDEX
    Explanations

    topics after abbreviations

    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
     it
    -2.56
     what
    -1.85
    </strong>
    -1.60
     their
    -1.59
     but
    -1.59
     the
    -1.57
     there
    -1.52
    :
    -1.52
     every
    -1.40
     at
    -1.39
    POSITIVE LOGITS
     partiellement
    1.58
     considérer
    1.44
     medes
    1.42
    
    1.41
    ⢪
    1.39
    Ρ
    1.38
    SSI
    1.37
    訁
    1.34
     dahin
    1.33
     étro
    1.33
    Activations Density 0.019%

    No Known Activations