© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6533
    Prev
    Next
    INDEX
    Explanations

    factual accuracy

    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
    Negative Logits
     transparence
    0.97
     σαν
    0.94
    ောင်း
    0.88
    antik
    0.84
    移植
    0.81
     સાર
    0.80
    leak
    0.79
    급
    0.79
     Injection
    0.78
     giz
    0.78
    POSITIVE LOGITS
     true
    1.90
    true
    1.82
    True
    1.78
     True
    1.69
     untrue
    1.62
     correct
    1.59
     TRUE
    1.59
     incorrect
    1.56
    TRUE
    1.50
    False
    1.39
    Activations Density 0.233%

    No Known Activations