© 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. 22-GEMMASCOPE-RES-131K
    7. 64778
    Prev
    Next
    INDEX
    Explanations

    code blocks and definitions

    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_22/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
     two
    -1.59
     other
    -1.50
     as
    -1.34
     all
    -1.32
    providedIn
    -1.30
     both
    -1.29
     Ufer
    -1.27
     still
    -1.27
     سایر
    -1.27
     three
    -1.22
    POSITIVE LOGITS
    ↵
    1.66
     geprü
    1.29
     haupts
    1.24
    Bjs
    1.22
     portent
    1.21
     normalerweise
    1.20
    
    1.16
     participer
    1.14
     uſe
    1.12
     gegebenen
    1.10
    Activations Density 0.000%

    No Known Activations