© 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. 6819
    Prev
    Next
    INDEX
    Explanations

    IP address

    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
     hei
    1.01
    苦
    0.93
    缕
    0.90
     corrections
    0.89
     assertions
    0.89
    THERE
    0.88
    CLS
    0.87
     כי
    0.87
    rolled
    0.86
     миру
    0.86
    POSITIVE LOGITS
    zy
    1.56
    zo
    1.30
    zie
    1.29
    za
    1.24
    ZA
    1.20
    epam
    1.18
    𝐳
    1.13
    ziert
    1.12
    zym
    1.11
    zed
    1.11
    Activations Density 0.061%

    No Known Activations