© 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. 1137
    Prev
    Next
    INDEX
    Explanations

    introducing comparative tables

    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
    ．
    0.83
    ／
    0.81
    ماً
    0.79
     „
    0.72
     /
    0.72
    ・・・
    0.72
    nić
    0.68
    اً
    0.68
    راً
    0.66
     deverá
    0.66
    POSITIVE LOGITS
     concurred
    0.86
     consisted
    0.80
    ).}
    0.79
     lorry
    0.78
    .”.
    0.77
     inning
    0.77
     strolled
    0.77
     contrasted
    0.76
     tidy
    0.75
    –
    0.74
    Activations Density 0.576%

    No Known Activations