© 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. 209
    Prev
    Next
    INDEX
    Explanations

    number 2

    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
     siete
    0.93
     ১৩
    0.85
     triplets
    0.85
    
    0.84
     thirteen
    0.83
     шести
    0.81
     seventh
    0.79
     tenfold
    0.79
     sétimo
    0.79
     Thirteen
    0.78
    POSITIVE LOGITS
    2
    3.41
    ２
    3.10
    ۲
    2.82
    𝟐
    2.81
    𝟮
    2.79
     ٢
    2.74
    ٢
    2.74
     ၂
    2.61
     ۲
    2.60
    ၂
    2.55
    Activations Density 3.093%

    No Known Activations