© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1320
    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
    いただけ
    0.87
    ='')
    0.76
    υτό
    0.74
    ரிகிறது
    0.73
    ="")
    0.72
    ocious
    0.72
    ')[
    0.72
    =")
    0.71
    えば
    0.70
    '})
    0.69
    POSITIVE LOGITS
     these
    4.27
    these
    4.11
    這些
    4.09
    这些
    4.07
    これらの
    3.94
    เหล่านี้
    3.89
    它们
    3.85
    These
    3.82
     THESE
    3.67
    它們
    3.65
    Activations Density 5.249%

    No Known Activations