© 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. 1582
    Prev
    Next
    INDEX
    Explanations

    asking for help or solution

    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
    储存
    -1.23
     trajo
    -0.91
    getDatabase
    -0.90
    loha
    -0.88
     THEN
    -0.87
     методом
    -0.87
     DBMS
    -0.86
     кӀош
    -0.86
    leges
    -0.86
     ENTER
    -0.86
    POSITIVE LOGITS
     impacted
    1.02
    וּ
    1.01
     fichero
    0.94
     folks
    0.93
     storici
    0.86
     couple
    0.84
     mencionar
    0.84
    ぐらい
    0.84
     ExecuteAsync
    0.82
     παι
    0.81
    Activations Density 0.652%

    No Known Activations