© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7643
    Prev
    Next
    INDEX
    Explanations

    worn, carved, single objects

    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_22_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
     李
    1.29
     王
    1.19
     Choi
    1.19
    uyen
    1.18
     Tsai
    1.16
    hyun
    1.12
     劉
    1.11
    尹
    1.11
     Kwon
    1.10
     Chiang
    1.10
    POSITIVE LOGITS
     Evol
    1.04
    Wisconsin
    1.00
     Scratch
    0.95
     modal
    0.92
     Oklahoma
    0.88
    Oklahoma
    0.88
     Wisconsin
    0.88
     Waz
    0.87
     Filtr
    0.86
     রাশিয়ার
    0.86
    Activations Density 0.049%

    No Known Activations