© 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-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5361
    Prev
    Next
    INDEX
    Explanations

    Kubernetes service configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ы
    0.99
    ску
    0.91
    স্ট
    0.91
     Madeline
    0.89
    Acrylic
    0.88
     Epit
    0.88
    ORF
    0.88
    includes
    0.87
    সংখ্যা
    0.87
     EXISTING
    0.87
    POSITIVE LOGITS
    個セット
    0.97
     مرة
    0.94
    ahaman
    0.94
     കൊണ്ട
    0.88
     forts
    0.87
    莠
    0.87
     bâtiment
    0.84
     keer
    0.84
     simplement
    0.84
     vacc
    0.83
    Activations Density 0.002%

    No Known Activations