© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    offering resources and support

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    \
    1.55
    \@
    1.22
    %\
    1.21
     \
    1.05
     %\
    1.04
    %%\
    1.04
    ~\
    0.98
    ...\
    0.95
    \!
    0.92
    \!\
    0.92
    POSITIVE LOGITS
     vary
    0.62
     Aircraft
    0.60
     있고
    0.57
     unpredictable
    0.57
     aircraft
    0.56
    xE
    0.56
     ई
    0.56
    .],
    0.55
    ResBuffer
    0.54
    വൃത്തി
    0.54
    Activations Density 0.022%

    No Known Activations