© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2337
    Prev
    Next
    INDEX
    Explanations

    Unto

    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_17_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
    ................
    1.07
     ..............
    0.98
     版本
    0.97
     .........
    0.96
     ..........
    0.95
    률
    0.93
     yüks
    0.91
    ylation
    0.90
     교
    0.89
     ........
    0.88
    POSITIVE LOGITS
    elizmente
    1.55
    ientras
    1.50
    though
    1.49
    жели
    1.43
    etheless
    1.42
    ونکہ
    1.42
    ecause
    1.39
    tanto
    1.34
    anmoins
    1.32
    aunque
    1.31
    Activations Density 0.458%

    No Known Activations