© 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. 34-GEMMASCOPE-RES-131K
    7. 93350
    Prev
    Next
    INDEX
    Explanations

    java class definitions or imports

    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
    仙
    -0.85
     bądź
    -0.77
     congregation
    -0.77
    jän
    -0.76
    حيات
    -0.76
     doGet
    -0.75
     profit
    -0.74
    殤
    -0.74
    𝘳
    -0.74
    傳
    -0.71
    POSITIVE LOGITS
     javax
    1.94
    javax
    1.47
    swing
    1.01
    onents
    0.84
     notare
    0.81
     geweldig
    0.81
    тиза
    0.81
    žiai
    0.79
     swing
    0.78
    ここでは
    0.77
    Activations Density 0.001%

    No Known Activations