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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1941
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ।'
    2.24
    ...'
    2.06
    '.
    2.05
    '।
    2.02
    '
    1.95
    '،
    1.88
    '."
    1.84
    ',
    1.81
    .'
    1.79
    '...
    1.76
    POSITIVE LOGITS
     “
    6.59
     “‘
    5.99
     “[
    5.64
     “…
    5.48
     “(
    5.42
    “
    5.12
     “”
    5.11
     ”
    4.91
     “.
    4.77
     ‘
    4.74
    Activations Density 5.767%

    No Known Activations