© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3717
    Prev
    Next
    INDEX
    Explanations

    to use, to meet, to replace

    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
    堡
    0.71
     cas
    0.64
     कार
    0.64
    क्स्ट
    0.62
     gór
    0.62
     कला
    0.61
     captain
    0.61
    captain
    0.61
    캡
    0.60
     sam
    0.59
    POSITIVE LOGITS
    седнев
    0.72
    fico
    0.66
     integrable
    0.64
    愍
    0.64
    몫
    0.63
     मातर
    0.62
     revoc
    0.62
     pith
    0.62
    リット
    0.61
    کو
    0.61
    Activations Density 0.251%

    No Known Activations