© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12885
    Prev
    Next
    INDEX
    Explanations

    listing items / and so on

    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
    Negative Logits
     shamb
    1.21
    锤
    1.18
     devast
    1.08
     startled
    1.07
     embarking
    1.05
     braced
    1.04
     overcrowding
    1.00
    semer
    1.00
     distraught
    0.99
     devastation
    0.99
    POSITIVE LOGITS
    代理
    1.15
     bribe
    1.11
     proxy
    1.08
    賄
    1.06
     bribes
    1.05
    VIP
    1.04
     proxies
    1.02
     bribery
    1.02
    shortcuts
    1.01
    proxy
    0.99
    Activations Density 0.236%

    No Known Activations