© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 789
    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
     savvy
    0.79
     belliger
    0.78
     geospatial
    0.77
     legitimacy
    0.76
     \%,
    0.72
     tinkering
    0.72
     \%$.
    0.70
     “[
    0.69
     。,
    0.69
     discerning
    0.69
    POSITIVE LOGITS
     కూడా
    0.89
    Retired
    0.85
    Longueur
    0.84
    CLOSED
    0.83
     וח
    0.83
    Untitled
    0.83
    Finale
    0.81
    también
    0.81
    SPECIAL
    0.80
    𓃵
    0.79
    Activations Density 1.049%

    No Known Activations