© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    LGBTQ youth 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
    باً
    0.91
     naciones
    0.90
     utilizing
    0.88
     Utilizing
    0.83
     utilize
    0.81
    راً
    0.80
    اً
    0.80
     वो
    0.78
     vanwege
    0.77
     القوه
    0.76
    POSITIVE LOGITS
     François
    1.50
     CNRS
    1.47
     Sébastien
    1.44
     Parisian
    1.41
    François
    1.38
     Toulouse
    1.37
     Clément
    1.36
     Conseil
    1.35
     Alsace
    1.35
     Stéphane
    1.34
    Activations Density 0.792%

    No Known Activations