© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8419
    Prev
    Next
    INDEX
    Explanations

    times and scales

    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
     Township
    0.95
    ாண
    0.90
    MCS
    0.89
     प्रखंड
    0.89
    mib
    0.87
     MCS
    0.86
    楯
    0.84
    ビーチ
    0.83
     consignment
    0.82
     Cors
    0.81
    POSITIVE LOGITS
     times
    2.08
    倍
    2.08
     倍
    1.97
     TIMES
    1.94
    fold
    1.89
     tenfold
    1.89
    times
    1.87
     twice
    1.87
     veces
    1.86
     lần
    1.82
    Activations Density 0.153%

    No Known Activations