© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8365
    Prev
    Next
    INDEX
    Explanations

    eigenvalues and eigenvectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     eutectic
    0.39
     /ˈ
    0.37
     substituent
    0.37
    א
    0.36
     rescaling
    0.36
    違
    0.36
    ֻ
    0.36
     א
    0.36
     הי
    0.36
     מו
    0.35
    POSITIVE LOGITS
    if
    0.41
    ikov
    0.41
    while
    0.40
    for
    0.39
    send
    0.38
    zki
    0.38
    ishment
    0.35
    lan
    0.34
    کلی
    0.33
     autoridades
    0.33
    Activations Density 0.079%

    No Known Activations