© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148433
    Prev
    Next
    INDEX
    Explanations

    household, family, utilities, sounds

    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_262k_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
     reco
    0.85
     segar
    0.81
     Recife
    0.80
     gewonnen
    0.74
    ✞
    0.73
     Nickelodeon
    0.71
    plica
    0.70
     excess
    0.69
    葱
    0.69
     Nä
    0.69
    POSITIVE LOGITS
    伪
    0.82
    mä
    0.68
    ည်
    0.66
    为此
    0.66
    utilise
    0.65
    grid
    0.64
    bourg
    0.64
    ೪
    0.62
     replied
    0.62
    warming
    0.62
    Activations Density 0.000%

    No Known Activations