© 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. 1986
    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
     diſ
    0.80
     theſe
    0.74
    ᗜ
    0.69
    瓔
    0.67
     moſt
    0.67
     thoſe
    0.66
    ൨
    0.65
     विभ
    0.64
    楢
    0.64
    ี่ป
    0.63
    POSITIVE LOGITS
    SB
    1.66
     SB
    1.63
    SU
    1.56
    Sulf
    1.55
    SV
    1.55
     SJ
    1.54
    SII
    1.53
     sú
    1.52
    SJ
    1.52
    Sul
    1.52
    Activations Density 3.673%

    No Known Activations