© 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. 14021
    Prev
    Next
    INDEX
    Explanations

    our methodology

    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
     homegrown
    1.31
    晓
    1.30
     southernmost
    1.27
     méridionale
    1.26
    eliest
    1.22
     chargée
    1.21
     sandwiched
    1.20
     núcleo
    1.19
    最后的
    1.18
    ónicas
    1.17
    POSITIVE LOGITS
     =
    1.09
    ))
    1.01
     انع
    1.01
     g
    1.01
     Symptoms
    1.00
     G
    0.99
    ↵↵
    0.98
    z
    0.97
     is
    0.97
     c
    0.97
    Activations Density 0.128%

    No Known Activations