© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60337
    Prev
    Next
    INDEX
    Explanations

    java.time 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
    SENSOR
    -0.75
    Intérieur
    -0.74
    mandu
    -0.73
    Vii
    -0.72
    XVI
    -0.71
     Groupe
    -0.71
    QK
    -0.71
    Grip
    -0.70
     alertness
    -0.70
    SCENE
    -0.69
    POSITIVE LOGITS
    廚房
    0.81
     Dre
    0.73
     வெ
    0.72
    в
    0.67
    žem
    0.66
    íc
    0.65
     enable
    0.65
     Mega
    0.65
     Gage
    0.65
     stesse
    0.63
    Activations Density 0.066%

    No Known Activations