© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14586
    Prev
    Next
    INDEX
    Explanations

    than peak summer

    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_13_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
     Gosudarstvennyj
    1.39
     параметр
    1.38
     белги
    1.36
    ви
    1.33
    ым
    1.27
     архив
    1.26
    깆
    1.24
     даних
    1.22
     же
    1.21
    Ž
    1.20
    POSITIVE LOGITS
     only
    1.12
     where
    1.01
     reviewed
    1.00
     reviewing
    1.00
     upward
    0.99
     single
    0.99
     knocking
    0.96
     upwards
    0.95
     published
    0.94
     applied
    0.94
    Activations Density 0.007%

    No Known Activations