© 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-16K
    7. 311
    Prev
    Next
    INDEX
    Explanations

    Do you want me to

    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
    liy
    0.62
    lor
    0.61
     severally
    0.60
    m
    0.59
    ]$
    0.57
    权重
    0.56
     portraying
    0.56
    listening
    0.55
    la
    0.55
    lak
    0.54
    POSITIVE LOGITS
    점이
    0.75
     管
    0.72
    ppler
    0.68
     reste
    0.65
    的不
    0.65
    점을
    0.64
    점
    0.64
     lembrar
    0.64
    Radiux
    0.64
    ctrine
    0.63
    Activations Density 0.395%

    No Known Activations