© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5745
    Prev
    Next
    INDEX
    Explanations

    in or on context

    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_17_width_16k_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
    虢
    0.91
     ഐ
    0.87
    ::<
    0.82
     }^{\
    0.81
    ╭
    0.80
     }^{(
    0.79
     gerektiğini
    0.78
     Woh
    0.78
     enclosing
    0.78
    🏼
    0.78
    POSITIVE LOGITS
     dossiers
    0.94
     guise
    0.94
     busque
    0.91
     процессе
    0.85
     retrospect
    0.84
    рожден
    0.84
     stedet
    0.83
    िमा
    0.83
     elke
    0.83
     каждом
    0.83
    Activations Density 0.335%

    No Known Activations