© 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. 34-GEMMASCOPE-RES-131K
    7. 91725
    Prev
    Next
    INDEX
    Explanations

    GlobalKey and programming identifiers

    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_34/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
    ائرة
    -0.82
     социально
    -0.80
    lord
    -0.80
    ིན་
    -0.77
    ämp
    -0.75
    ͧ
    -0.75
     auroit
    -0.75
    ͪ
    -0.74
    lace
    -0.73
     Ausblick
    -0.73
    POSITIVE LOGITS
     key
    0.91
    Marca
    0.91
     Key
    0.85
    Key
    0.84
     unique
    0.84
     KEY
    0.84
     Wex
    0.80
     prospec
    0.79
     パソコン
    0.78
    фіка
    0.77
    Activations Density 0.001%

    No Known Activations