© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    exams

    np_acts-logits-general · gemini-2.5-flash-lite

    exam or test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \:
    0.44
     Plant
    0.43
    certificate
    0.41
     العام
    0.40
     productive
    0.39
     Optimize
    0.39
    &#
    0.39
     Growers
    0.39
    _
    0.39
     Ubuntu
    0.39
    POSITIVE LOGITS
     గురించి
    0.55
     ಪೊಲೀಸ
    0.50
    鈣
    0.48
     ಕಾ
    0.46
    煒
    0.45
    ড়ার
    0.43
     ಪ್ರಯ
    0.43
     recueill
    0.43
    ដែលអាច
    0.43
    paysys
    0.43
    Activations Density 0.004%

    No Known Activations