© 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. 10741
    Prev
    Next
    INDEX
    Explanations

    Okay, let’s explain

    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
     infin
    1.06
     tanning
    1.04
    мна
    1.03
    ⁩
    1.03
    ッカー
    1.03
    六
    1.02
    modules
    1.00
     SafeArea
    0.99
     उम्मीद
    0.98
    assuming
    0.98
    POSITIVE LOGITS
    liness
    1.79
     magnitude
    1.03
    lies
    1.01
    ly
    0.95
    liest
    0.88
    ings
    0.86
     perpetuate
    0.86
    晰
    0.85
    linge
    0.85
     макси
    0.85
    Activations Density 0.044%

    No Known Activations