© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3852
    Prev
    Next
    INDEX
    Explanations

    key takeaways

    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
     apiClient
    1.94
    런
    1.87
    hato
    1.86
    ջ
    1.85
    ਗੇ
    1.84
     कदमों
    1.84
    irm
    1.84
     रेन
    1.82
    streng
    1.82
    很多的
    1.82
    POSITIVE LOGITS
    s
    2.40
    Ephemeral
    2.22
    sus
    1.99
    ยุ
    1.96
    tive
    1.95
    t
    1.93
    nth
    1.92
    sman
    1.90
    Queue
    1.87
    nW
    1.86
    Activations Density 0.110%

    No Known Activations