© 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. 6185
    Prev
    Next
    INDEX
    Explanations

    html tags

    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
     prior
    0.93
    ifically
    0.92
     initialized
    0.86
     healed
    0.86
     reduced
    0.85
     satisfying
    0.83
     demanding
    0.83
    疳
    0.82
     renamed
    0.82
    पहले
    0.81
    POSITIVE LOGITS
    ください
    0.88
    </body>
    0.87
    ю
    0.84
    there
    0.83
     DbSet
    0.82
     verder
    0.82
    Time
    0.81
    TER
    0.81
    Tea
    0.80
     conférences
    0.80
    Activations Density 0.076%

    No Known Activations