© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5890
    Prev
    Next
    INDEX
    Explanations

    20

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     hashing
    0.94
     hypergeometric
    0.86
    Coref
    0.83
    迠
    0.82
    ্লিশ
    0.82
    vislosti
    0.82
     collaborateurs
    0.81
     FFT
    0.81
     ئەم
    0.80
     गुजराती
    0.80
    POSITIVE LOGITS
    0
    0.74
     igjen
    0.71
    1
    0.71
        
    0.70
    太大
    0.70
    ाम
    0.70
    温
    0.69
     والله
    0.68
    نت
    0.68
     selben
    0.66
    Activations Density 0.001%

    No Known Activations