© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14825
    Prev
    Next
    INDEX
    Explanations

    foreign scripts or language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    3.30
     fonbet
    3.14
    ถุน
    3.00
    symmetric
    2.89
    ్వర
    2.87
    sab
    2.86
    ات
    2.84
    ात
    2.77
    sion
    2.77
    traj
    2.75
    POSITIVE LOGITS
    vaar
    2.16
     e
    2.16
     se
    2.08
     s
    2.03
    ass
    2.03
     الامر
    2.00
     m
    1.99
     lives
    1.97
     сме
    1.95
    गी
    1.93
    Activations Density 0.015%

    No Known Activations