© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2386
    Prev
    Next
    INDEX
    Explanations

    font similarity

    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_13_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
    <unused709>
    1.17
    옆
    1.16
     отметить
    1.16
    டக்கலை
    1.13
    는데요
    1.13
    рсә
    1.12
    Ironically
    1.10
    Benzoimidazole
    1.08
     옆
    1.08
    however
    1.07
    POSITIVE LOGITS
     وأن
    1.10
     capaz
    0.99
     capazes
    0.96
     capable
    0.95
     capaces
    0.94
     якобы
    0.90
     legitimate
    0.90
     लायक
    0.89
     “
    0.89
     viable
    0.88
    Activations Density 0.732%

    No Known Activations