© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 47399
    Prev
    Next
    INDEX
    Explanations

    violet, purple

    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_16_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
     in
    1.29
     on
    1.02
     an
    1.02
     في
    0.99
    s
    0.99
    Р
    0.98
     the
    0.96
     agus
    0.95
    the
    0.93
    you
    0.93
    POSITIVE LOGITS
    рио
    1.09
     violet
    1.09
    ate
    1.08
    اری
    0.93
    Violet
    0.88
     Violet
    0.86
    arini
    0.86
    .
    0.86
     purple
    0.85
    violet
    0.82
    Activations Density 0.008%

    No Known Activations