© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10571
    Prev
    Next
    INDEX
    Explanations

    public java keywords

    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
    ฯ
    0.98
     VICTOR
    0.97
    之外
    0.92
     thérapeut
    0.88
     কোথায়
    0.87
     hey
    0.87
    ѓ
    0.86
    之上
    0.85
    在哪
    0.83
     دائما
    0.83
    POSITIVE LOGITS
     billions
    1.16
     millions
    1.16
    Os
    1.08
    thousands
    1.06
    ints
    1.03
     thousands
    1.03
     hundreds
    1.00
    Mes
    0.98
     bloodstream
    0.97
    ்டு
    0.96
    Activations Density 0.027%

    No Known Activations