© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71754
    Prev
    Next
    INDEX
    Explanations

    jacks, whatsapp, and fast tracks

    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
     costuras
    -1.63
     enthusiastic
    -1.38
     one
    -1.38
     flechas
    -1.34
     seven
    -1.34
     sombras
    -1.33
     puntas
    -1.33
    initWith
    -1.33
     tubos
    -1.31
     ΤΟ
    -1.31
    POSITIVE LOGITS
    或者是
    1.48
    などに
    1.44
    !!!!!!!
    1.39
    !!!!!!
    1.35
     !!!!
    1.29
    なども
    1.27
    撂
    1.26
     cursory
    1.25
     unending
    1.23
     overarching
    1.22
    Activations Density 0.010%

    No Known Activations