© 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. 8861
    Prev
    Next
    INDEX
    Explanations

    Caity Lotz, feeling, doing, laboratory

    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
     testified
    0.90
    ادار
    0.90
     Equilib
    0.89
    🎰
    0.88
     قاب
    0.84
     неред
    0.84
     наиболь
    0.83
    рио
    0.83
     maximum
    0.83
     unforeseen
    0.83
    POSITIVE LOGITS
    Highly
    1.06
    लीन
    1.03
     highly
    1.02
    メ
    1.02
    highly
    1.01
    ｮ
    0.99
    っ
    0.96
     메
    0.95
     mundo
    0.94
    nitz
    0.94
    Activations Density 0.002%

    No Known Activations