© 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. 115640
    Prev
    Next
    INDEX
    Explanations

    movement and direction

    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
     повер
    -0.82
    րի
    -0.75
     можешь
    -0.73
     можем
    -0.71
    ⠛
    -0.70
    userLogin
    -0.68
     році
    -0.67
     Геор
    -0.66
     Tripod
    -0.64
     eten
    -0.63
    POSITIVE LOGITS
     back
    4.06
    Back
    2.77
    back
    2.36
     Back
    2.25
    BACK
    2.20
     BACK
    2.14
     туда
    1.99
    зад
    1.88
     backwards
    1.81
     왕
    1.68
    Activations Density 0.078%

    No Known Activations