© 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. 8401
    Prev
    Next
    INDEX
    Explanations

    "Le" followed by common words

    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
     essai
    1.34
     éd
    1.34
     édition
    1.33
     écran
    1.31
     area
    1.30
     endroit
    1.29
     étude
    1.29
    お
    1.29
     alternative
    1.27
     ens
    1.27
    POSITIVE LOGITS
    麼
    1.04
     जता
    0.96
    творю
    0.95
    רום
    0.93
    ข้าง
    0.86
    로부터
    0.86
     telles
    0.85
    ২৭
    0.84
    <unused2166>
    0.84
    rous
    0.84
    Activations Density 0.017%

    No Known Activations