© 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. 67573
    Prev
    Next
    INDEX
    Explanations

    needed to, affairs and, normally come

    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
     when
    -1.36
     >(
    -1.32
    /**/
    -1.30
     carlo
    -1.28
        
    -1.25
     
    -1.25
     garcia
    -1.23
     
    -1.23
     feveral
    -1.23
     \
    -1.23
    POSITIVE LOGITS
    その
    1.57
    ltä
    1.40
     –
    1.34
     incluyendo
    1.34
    也就是
    1.30
     his
    1.26
     suoi
    1.25
    其他
    1.23
     otras
    1.23
    他の
    1.20
    Activations Density 0.283%

    No Known Activations