© 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. 9619
    Prev
    Next
    INDEX
    Explanations

    The Guardian

    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
    軟
    0.89
     Heads
    0.81
    shaft
    0.81
     नर्म
    0.79
     кон
    0.79
    پیش
    0.79
     enkel
    0.78
    直至
    0.78
    맹
    0.76
     приступи
    0.76
    POSITIVE LOGITS
    described
    1.19
    labelledby
    1.11
     bestowed
    1.06
     pinning
    1.05
    ̙
    1.04
     assays
    1.01
     atrocious
    1.00
     crise
    1.00
     ($(
    0.99
    UTONIUM
    0.99
    Activations Density 0.000%

    No Known Activations