© 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. 9174
    Prev
    Next
    INDEX
    Explanations

    offering support and resources

    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
    ър
    0.84
     passa
    0.77
    っぱり
    0.77
     nadi
    0.76
    ンの
    0.75
    ნენ
    0.75
    莨
    0.74
     バス
    0.74
     evanescent
    0.74
     mansions
    0.73
    POSITIVE LOGITS
     CDT
    1.03
     Except
    0.99
    Wil
    0.94
    athlet
    0.93
     ზე
    0.92
     Wil
    0.87
     WIL
    0.87
     కని
    0.87
    IPC
    0.87
     postale
    0.86
    Activations Density 0.027%

    No Known Activations