© 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. 8749
    Prev
    Next
    INDEX
    Explanations

    CPU cores and GPU memory

    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
     microfilm
    0.80
    苛
    0.76
    nP
    0.71
    дон
    0.71
    JAN
    0.71
    鬢
    0.69
    小物
    0.67
    ジア
    0.67
     অধিনায়ক
    0.66
    gleich
    0.66
    POSITIVE LOGITS
     karşı
    1.02
    তারা
    0.93
     Fauci
    0.91
     falta
    0.91
     darf
    0.90
     Emer
    0.89
    Emer
    0.88
     izol
    0.88
     dürfen
    0.86
     musst
    0.86
    Activations Density 0.083%

    No Known Activations