© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16421
    Prev
    Next
    INDEX
    Explanations

    carbon compounds and carbonara

    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
    c
    0.94
    。,
    0.91
    ajj
    0.87
    الی
    0.82
    ول
    0.81
    。
    0.79
    एफ
    0.78
    $`
    0.78
    ।
    0.77
    एस
    0.77
    POSITIVE LOGITS
    ن
    1.09
    an
    1.03
    ন
    0.99
    ми
    0.98
    ру
    0.98
    ं
    0.97
    es
    0.96
    ে
    0.96
    nél
    0.96
    ية
    0.95
    Activations Density 0.006%

    No Known Activations