© 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-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1590
    Prev
    Next
    INDEX
    Explanations

    radiant shine and light

    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
     plantations
    0.74
    狎
    0.73
     हळ
    0.72
     Khalil
    0.72
    setVertical
    0.70
     traged
    0.69
    entropy
    0.69
    ന്ത്ര
    0.68
    衲
    0.67
     indoctr
    0.67
    POSITIVE LOGITS
     shine
    3.25
     shining
    3.02
     shines
    2.95
     sparkle
    2.91
     shone
    2.84
     sparkles
    2.76
     sparkling
    2.73
     shiny
    2.60
     glittering
    2.60
     Shine
    2.60
    Activations Density 0.749%

    No Known Activations