© 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. 17-GEMMASCOPE-2-RES-16K
    7. 383
    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_17_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
    \|=
    0.97
    wiście
    0.83
    stderr
    0.81
     cittam
    0.81
     DESCRIPTION
    0.79
     अभिक
    0.79
     раствора
    0.79
    婢
    0.79
     وقتی
    0.77
     কথ
    0.76
    POSITIVE LOGITS
     winter
    3.53
     year
    3.42
     season
    3.41
     summer
    3.36
     autumn
    3.23
     Year
    3.21
     musim
    3.15
     Winter
    3.11
     YEAR
    3.06
    winter
    3.05
    Activations Density 7.264%

    No Known Activations