© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3010
    Prev
    Next
    INDEX
    Explanations

    reason or purpose

    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_29_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
    ed
    1.08
    ة
    1.04
    Metadata
    0.87
    Information
    0.85
    ️
    0.85
    Having
    0.85
    rivial
    0.82
    А
    0.81
    payload
    0.79
     त्यासाठी
    0.78
    POSITIVE LOGITS
     purposes
    1.60
     use
    1.30
     optimum
    1.29
     awhile
    1.24
     sake
    1.23
     maximum
    1.18
     greatness
    1.18
     обозна
    1.15
    erun
    1.15
     chacune
    1.14
    Activations Density 0.410%

    No Known Activations