© 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. 5778
    Prev
    Next
    INDEX
    Explanations

    beyond simple and traditional

    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
    饗
    0.98
     Conexion
    0.97
     podp
    0.96
     conexion
    0.96
     particip
    0.95
     Augmented
    0.93
     &#
    0.92
     rendez
    0.89
     ALT
    0.89
     �
    0.88
    POSITIVE LOGITS
     versatile
    1.20
     easiest
    1.10
    relatively
    1.08
     ويمكن
    1.08
     dễ
    1.04
    ható
    1.03
    เหมาะ
    1.01
     freestanding
    1.00
    ストレス
    1.00
     mammalian
    1.00
    Activations Density 0.189%

    No Known Activations