© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 501
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     characters
    0.53
    ndon
    0.51
     thing
    0.50
    ھوں
    0.48
     넘
    0.47
    തമായ
    0.47
     way
    0.47
     hes
    0.47
     person
    0.46
    ierung
    0.46
    POSITIVE LOGITS
    ູ່
    0.59
    縮
    0.58
    abhas
    0.55
     iub
    0.55
     கிரேக்க
    0.54
    เสน
    0.53
    beq
    0.53
    bearing
    0.53
    CUT
    0.53
    ρούν
    0.52
    Activations Density 1.722%

    No Known Activations