© 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. 831
    Prev
    Next
    INDEX
    Explanations

    collagen and DNA

    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
     Moura
    1.08
     हॉकी
    1.05
     Gül
    1.05
     unemployed
    1.04
    谢
    1.01
     Rodeo
    1.00
     Figue
    1.00
     월
    1.00
    火箭
    0.99
     disillusion
    0.98
    POSITIVE LOGITS
     genetic
    2.74
     alleles
    2.71
     genes
    2.68
     DNA
    2.66
     genome
    2.61
     allele
    2.59
     Genetic
    2.56
    Genetic
    2.56
     gene
    2.52
     chromosome
    2.52
    Activations Density 0.971%

    No Known Activations